Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

docs(mcp): document the census API, per-tool pages and count markers, and ship the changelog entry and refreshed tool catalog

nirholasc91713a27310
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 8e4463d37..04e1c4f5f 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -38,6 +38,7 @@ Public history for [three.ws](https://three.ws), newest first. New pages come fr
- **Approve your agents' payments from a notification**: Set any agent spend rule to Ask me and the agent now waits for your yes instead of failing. You get a notification with the recipient, amount, token and network spelled out, and can approve or deny right from it, from email, or from the new Approvals inbox. Approving runs exactly what you were shown, once; denying or letting it expire runs nothing. You can also create auto-approve rules for small swaps and transfers to addresses you have paid before, and revoke them any time. (`/approvals`) `[feature]`
- **Coin logos, agent art and IPFS images load again**: Several public IPFS gateways started refusing image and metadata requests from websites this month, which left coin logos, the 3D coin face, agent cards and on-chain agent art blank or broken across the site. Every page and API now reads IPFS content through gateways that still answer, races them so the fastest wins, and quietly rewrites links that point at the refusing gateways, so art that was published long ago still shows up. Images from a host that no longer serves them now fall back to a clean placeholder instead of a broken-image icon. (`/launches`) `[fix, improvement]`
- **Developer plans with quotas that are enforced, self-serve upgrades, key rotation, IP allowlists and per-key analytics**: Every API key now sits on a developer plan: Free, Builder, Scale or Enterprise, each with a monthly call quota, a per-minute burst ceiling, a concurrency ceiling and a webhook cap, all enforced on every /api/v1 call rather than only recorded. Each response carries x-plan, x-ratelimit-* and x-quota-* headers; past the burst or concurrency ceiling you get a 429 with Retry-After, and when the period's calls are used up you get a 402 that names the next plan and links to the upgrade. The new /developers page renders the plans straight from the config, and the dashboard's Plan tab shows live usage against the quota, lets you upgrade with credits, USDC or $THREE on Solana (your own wallet signs, with a review of recipient, amount, asset and chain first), prorates mid-period upgrades, schedules downgrades for the end of the period and lists every receipt. Revoking a key now takes effect immediately on every server. Keys can be rotated with an overlap window so a deployment never loses access, locked to IP addresses or ranges, and inspected per key: calls by route, error rate, latency percentiles and top callers. (`/developers`) `[feature, sdk, security, docs]`
+- **Every MCP tool now has its own page, and the tool counts are measured, not typed**: The MCP tool catalog now shows the real totals for every server, worked out from the live servers with a plain note on how, and a release view that lists which tools each release added. Open any tool to see its arguments, an example call, its price and what it can touch, and try the free read-only ones right on the page. You can filter the catalog by category. Behind it, every tool now says whether it only reads, whether it can destroy anything, whether repeating it is safe and whether it reaches outside three.ws, and every tool says when to use it. Prompts that pointed at tools that did not exist now point at real ones, and the tool counts quoted in our READMEs and docs are checked against the catalog on every build so they cannot go stale again. (`/mcp-tools`) `[feature, improvement]`
- **Import skills from any registry, safely**: Agents can now take skills from outside three.ws. Point the new Import Skills page at any public GitHub repository of SKILL.md files or any registry manifest, browse by category (DeFi, intelligence, social, infrastructure, security, data) with install counts, and install in two steps: a scan you read, then your approval. Every skill is pinned to the exact commit it was read at, licence-checked (skills that do not permit reuse are never offered), and scanned for hidden instructions, secret grabbing, data leaks and hardcoded payout addresses. Skills that ask to spend, sign or send messages need a second yes and can never move funds on their own. Updates never apply silently: you see the diff and approve it. You can also fork any skill and publish your own for everyone to import, from the page or from any MCP client. (`/skills/import`) `[feature, security]`
- **Launch a coin as a Uniswap pool on Base, and retry launches safely**: There is a new launch lane: your agent launches a fixed-supply coin whose whole supply sits in one Uniswap V3 pool on Base. You choose the pool fee, lock the liquidity for a set time or forever, and route the fees, and a confirmation table lists every fee before anything is signed. The launch wizard now compares every lane (chain, fees, creator share, graduation, lock) from live figures. Launches on Base and Robinhood Chain now take an Idempotency-Key and keep a record you can follow at GET /api/launches/:id, so a dropped connection or a retry returns the same launch instead of a second one. Solana stays the default lane. The Base lane opens once its launcher contract is deployed. (`/launch/uniswap`) `[feature]`
- **Live agent payments keep running when fee sponsorship pauses**: When the wallet that covers Solana network fees for agent payments runs low, agents on three.ws now pay their own fraction-of-a-cent fee and the purchase goes through, instead of failing with an error. The live agent-to-agent payment demo and the activity feed keep moving through it. (`/agent-exchange`) `[fix]`
@@ -1742,7 +1743,7 @@ And all of it is public. Oracle Lab publishes the actual model: every weight, th
- **Docs World (immersive 3D docs)** (`/docs/world`): The full three.ws documentation as a walkable 3D world: every docs section is a glowing pavilion, and the live pages render inside the scene.
- **Docs: Avatar CLI** (`/docs/avatar-cli`): Command reference for @three-ws/avatar-cli: init, validate, hash, and preview, with every flag, exit code, and JSON shape, plus the two checks that gate a release on your avatar manifest.
- **Examples** (`/examples`): Runnable three.ws examples: copy-paste snippets that execute on the page against the production CDN bundle, plus every example that ships in the repository, generated by scanning it. Each one lists the files it contains and the command that runs it.
-- **MCP Tool Catalog** (`/mcp-tools`): Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.
+- **MCP Tool Catalog** (`/mcp-tools`): Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.
- **Recipe: build a whole asset pack in parallel** (`/cookbook/parallel-asset-pack`): Fan a list of prompts across the free 3D lane at a sane concurrency, download every model, render a still of each, and emit a manifest plus a browsable gallery. Partial failure degrades instead of aborting the run.
- **Recipe: gate 3D assets in CI** (`/cookbook/asset-quality-gate`): Generated geometry fails quietly. This gate inspects every model against an explicit triangle, size, and material budget and exits non-zero, so a bad asset fails the build instead of the launch.
- **Recipe: give your AI assistant a 3D tool** (`/cookbook/mcp-3d-tool`): A Model Context Protocol server that exposes text-to-3D generation and model rendering as tools, so Claude Code, Claude Desktop, or Cursor can build and then actually look at 3D models mid-conversation.
diff --git a/STRUCTURE.md b/STRUCTURE.md
index 35bc4a350..c24997c8e 100644
--- a/STRUCTURE.md
+++ b/STRUCTURE.md
@@ -250,7 +250,7 @@ bottom.
| On-chain agent invocation | [contracts/agent-invocation/](contracts/agent-invocation) | In-repo | Anchor program: verifiable agent-to-agent skill invocation events. SDK: [agent-protocol-sdk/](agent-protocol-sdk) |
| Escrowed knocks (pay-per-reply) | [contracts/knock-escrow/](contracts/knock-escrow) | In-repo | Anchor program making a knock's payment conditional instead of final: `knock` parks the price in a vault owned by the knock's own PDA, and only three things can happen to it. `answer` pays the owner minus a fee capped at 10% in the program itself, `refuse` refunds the sender in full and takes no fee, and `reclaim` refunds the sender once the reply window closes and can be called by anyone. Each `KnockRecord` snapshots the fee that was in force when it was made, so an authority cannot reprice money already in escrow, and it stores only the SHA-256 of the message and the reply, never their text. The trust-me version of this settles straight to the owner at [api/knock/](api/knock) (row above); this is the version that works between strangers. Both sides are reachable from a browser: senders escrow and crank their own refund from the door page, owners open their on-chain door, answer for payment or refuse for a refund from [/knock](pages/knock.html), all signed by their own wallet ([src/knock/escrow-checkout.js](src/knock/escrow-checkout.js)). Docs: [contracts/knock-escrow/README.md](contracts/knock-escrow/README.md), [docs/knock.md](docs/knock.md). Tests: [tests/knock-escrow-program.test.js](tests/knock-escrow-program.test.js), [tests/knock-escrow-pda.test.js](tests/knock-escrow-pda.test.js), [tests/api-knock-escrowed.test.js](tests/api-knock-escrowed.test.js), [tests/api-knock-escrow-sync.test.js](tests/api-knock-escrow-sync.test.js) |
| Cross-chain SDKs | [sdk/](sdk), [solana-agent-sdk/](solana-agent-sdk), [agent-payments-sdk/](agent-payments-sdk), [agent-protocol-sdk/](agent-protocol-sdk) | Published | Cross-chain agent SDKs |
-| MCP integration | [mcp-server/](mcp-server), [mcp-bridge/](mcp-bridge), [packages/*-mcp/](packages) | 43 npm servers + 7 hosted remote (50 total, incl. the free `/api/mcp-studio` 3D Studio, whose ChatGPT plugin surface [api/mcp-chatgpt.js](api/mcp-chatgpt.js) `→ /api/mcp-chatgpt` serves the eight 3D tools and the model viewer without the persona tools or any `frameDomains`, and [api/mcp-grok.js](api/mcp-grok.js) `→ /api/mcp-grok` serves every studio tool with no widget templates plus, for a caller signed in with OAuth 2.1 or a connector key, the account's agent tools from the core server through [api/_mcp-studio/account-tools.js](api/_mcp-studio/account-tools.js), never a value-moving one ([tests/mcp-grok-accounts.test.js](tests/mcp-grok-accounts.test.js)); all three doors share [api/_mcp-studio/handler.js](api/_mcp-studio/handler.js), and `SURFACES` in [api/_mcp-studio/dispatch.js](api/_mcp-studio/dispatch.js) defines what each advertises), all in the [MCP registry](https://registry.modelcontextprotocol.io/?q=io.github.nirholas). Canonical metadata: [prompts/store-submissions/_generated/mcp-listing-source.json](prompts/store-submissions/_generated/mcp-listing-source.json), generated from the manifests by [scripts/build-mcp-listing-source.mjs](scripts/build-mcp-listing-source.mjs) (`npm run audit:mcp-listing` fails when it drifts) | Model Context Protocol surface, full server list in [docs/mcp.md](docs/mcp.md). One-click client setup: [pages/connect.html](pages/connect.html) `→ /connect` (Claude, Cursor and VS Code install links plus ChatGPT, Claude Code and generic steps, built live from [public/.well-known/mcp.json](public/.well-known/mcp.json) with tool counts from the catalog; config names match the CLI's `slugForPath`). CLI: [packages/three-ws-cli/](packages/three-ws-cli) (`npx three-ws setup`), docs [docs/cli.md](docs/cli.md) `→ /docs/cli`. One-command setup per client (`npx three-ws --claude`), `doctor`, `agent status` and `team` live in [packages/three-ws-cli/src/commands/](packages/three-ws-cli/src/commands); the hosted installers [public/cli/](public/cli) (`/cli/install`, `/cli/claude`, each with a `.sha256` and an ed25519 `.sig`, public key `signing-key.pem`) are signed by [scripts/sign-cli-scripts.mjs](scripts/sign-cli-scripts.mjs) (`npm run sign:cli`, verified by `npm run check:cli-scripts` in the gate); the clean-container check is [packages/three-ws-cli/tests/container/run.sh](packages/three-ws-cli/tests/container/run.sh). Searchable index of every tool: [pages/mcp-tools.html](pages/mcp-tools.html) `→ /mcp-tools`, rendered from the generated [public/mcp-catalog.json](public/mcp-catalog.json) ([scripts/build-mcp-catalog.mjs](scripts/build-mcp-catalog.mjs), `npm run build:mcp-catalog`, staleness gated by `npm run audit:mcp-catalog`). Tool safety annotations are verified against each handler by [scripts/audit-mcp-safety.mjs](scripts/audit-mcp-safety.mjs) (`npm run audit:mcp-safety`, rules in [scripts/lib/mcp-safety-check.mjs](scripts/lib/mcp-safety-check.mjs), guarded-file list shared with the golden snapshot via [scripts/lib/mcp-tool-sources.mjs](scripts/lib/mcp-tool-sources.mjs)); docs [docs/mcp-safety.md](docs/mcp-safety.md) `→ /docs/mcp-safety`. Trust policy: [api/mcp-policy.js](api/mcp-policy.js) `-> GET /api/mcp-policy` turns those verified labels into a ready-to-paste client allowlist (profiles strict/balanced/open x formats claude/vscode/json), surfaced by the builder panel on `/mcp-tools`. Connector-review readiness (every paid stdio tool answers a clean x402 challenge, and the reviewer entitlement lifts it): [scripts/audit-mcp-reviewer-path.mjs](scripts/audit-mcp-reviewer-path.mjs), `npm run audit:mcp-reviewer`. Tests: [tests/mcp-safety-audit.test.js](tests/mcp-safety-audit.test.js), [tests/mcp-catalog.test.js](tests/mcp-catalog.test.js), [tests/api/mcp-policy.test.js](tests/api/mcp-policy.test.js) |
+| MCP integration | [mcp-server/](mcp-server), [mcp-bridge/](mcp-bridge), [packages/*-mcp/](packages) | <!-- mcp-count:stdio.servers -->41<!-- /mcp-count --> npm servers + <!-- mcp-count:hosted.servers -->10<!-- /mcp-count --> hosted remote (<!-- mcp-count:all.servers -->51<!-- /mcp-count --> total, incl. the free `/api/mcp-studio` 3D Studio, whose ChatGPT plugin surface [api/mcp-chatgpt.js](api/mcp-chatgpt.js) `→ /api/mcp-chatgpt` serves the eight 3D tools and the model viewer without the persona tools or any `frameDomains`, and [api/mcp-grok.js](api/mcp-grok.js) `→ /api/mcp-grok` serves every studio tool with no widget templates plus, for a caller signed in with OAuth 2.1 or a connector key, the account's agent tools from the core server through [api/_mcp-studio/account-tools.js](api/_mcp-studio/account-tools.js), never a value-moving one ([tests/mcp-grok-accounts.test.js](tests/mcp-grok-accounts.test.js)); all three doors share [api/_mcp-studio/handler.js](api/_mcp-studio/handler.js), and `SURFACES` in [api/_mcp-studio/dispatch.js](api/_mcp-studio/dispatch.js) defines what each advertises), all in the [MCP registry](https://registry.modelcontextprotocol.io/?q=io.github.nirholas). Canonical metadata: [prompts/store-submissions/_generated/mcp-listing-source.json](prompts/store-submissions/_generated/mcp-listing-source.json), generated from the manifests by [scripts/build-mcp-listing-source.mjs](scripts/build-mcp-listing-source.mjs) (`npm run audit:mcp-listing` fails when it drifts) | Model Context Protocol surface, full server list in [docs/mcp.md](docs/mcp.md). One-click client setup: [pages/connect.html](pages/connect.html) `→ /connect` (Claude, Cursor and VS Code install links plus ChatGPT, Claude Code and generic steps, built live from [public/.well-known/mcp.json](public/.well-known/mcp.json) with tool counts from the catalog; config names match the CLI's `slugForPath`). CLI: [packages/three-ws-cli/](packages/three-ws-cli) (`npx three-ws setup`), docs [docs/cli.md](docs/cli.md) `→ /docs/cli`. One-command setup per client (`npx three-ws --claude`), `doctor`, `agent status` and `team` live in [packages/three-ws-cli/src/commands/](packages/three-ws-cli/src/commands); the hosted installers [public/cli/](public/cli) (`/cli/install`, `/cli/claude`, each with a `.sha256` and an ed25519 `.sig`, public key `signing-key.pem`) are signed by [scripts/sign-cli-scripts.mjs](scripts/sign-cli-scripts.mjs) (`npm run sign:cli`, verified by `npm run check:cli-scripts` in the gate); the clean-container check is [packages/three-ws-cli/tests/container/run.sh](packages/three-ws-cli/tests/container/run.sh). Per-tool pages (schema, example call, price, a try-it for free read-only tools): [pages/mcp-tool.html](pages/mcp-tool.html) `→ /mcp-tools/<server>/<tool>`. The census (tools, resources, prompts per server, with a how-it-is-calculated note) is computed at build time into [public/tools.json](public/tools.json) and at request time by [api/mcp-census.js](api/mcp-census.js) `→ /api/mcp-census` ([api/_lib/mcp-census.js](api/_lib/mcp-census.js)); the release-by-release diff of added tools is [public/mcp-tool-history.json](public/mcp-tool-history.json) ([scripts/build-mcp-tool-history.mjs](scripts/build-mcp-tool-history.mjs)); docs that quote a count use `<!-- mcp-count:... -->` markers that `npm run check:mcp-counts` ([scripts/check-mcp-counts.mjs](scripts/check-mcp-counts.mjs)) verifies in the gate, alongside [tests/mcp-tool-quality.test.js](tests/mcp-tool-quality.test.js) and [tests/mcp-prompt-references.test.js](tests/mcp-prompt-references.test.js) (`npm run test:mcp-surface`). Searchable index of every tool: [pages/mcp-tools.html](pages/mcp-tools.html) `→ /mcp-tools`, rendered from the generated [public/mcp-catalog.json](public/mcp-catalog.json) ([scripts/build-mcp-catalog.mjs](scripts/build-mcp-catalog.mjs), `npm run build:mcp-catalog`, staleness gated by `npm run audit:mcp-catalog`). Tool safety annotations are verified against each handler by [scripts/audit-mcp-safety.mjs](scripts/audit-mcp-safety.mjs) (`npm run audit:mcp-safety`, rules in [scripts/lib/mcp-safety-check.mjs](scripts/lib/mcp-safety-check.mjs), guarded-file list shared with the golden snapshot via [scripts/lib/mcp-tool-sources.mjs](scripts/lib/mcp-tool-sources.mjs)); docs [docs/mcp-safety.md](docs/mcp-safety.md) `→ /docs/mcp-safety`. Trust policy: [api/mcp-policy.js](api/mcp-policy.js) `-> GET /api/mcp-policy` turns those verified labels into a ready-to-paste client allowlist (profiles strict/balanced/open x formats claude/vscode/json), surfaced by the builder panel on `/mcp-tools`. Connector-review readiness (every paid stdio tool answers a clean x402 challenge, and the reviewer entitlement lifts it): [scripts/audit-mcp-reviewer-path.mjs](scripts/audit-mcp-reviewer-path.mjs), `npm run audit:mcp-reviewer`. Tests: [tests/mcp-safety-audit.test.js](tests/mcp-safety-audit.test.js), [tests/mcp-catalog.test.js](tests/mcp-catalog.test.js), [tests/api/mcp-policy.test.js](tests/api/mcp-policy.test.js) |
| Grok Bot integration | Door [api/mcp-grok.js](api/mcp-grok.js) `→ /api/mcp-grok` on the shared studio handler [api/_mcp-studio/](api/_mcp-studio), account tools [api/_mcp-studio/account-tools.js](api/_mcp-studio/account-tools.js), install tokens [api/mcp-studio/install.js](api/mcp-studio/install.js), landing page [pages/grok.html](pages/grok.html) `→ /grok`, skill file [public/grok-skill.md](public/grok-skill.md) (template [data/grok-skill-md.template.md](data/grok-skill-md.template.md)), `/connect` Grok Bot tab [pages/connect.html](pages/connect.html), connector probe [scripts/mcp-client-probe.mjs](scripts/mcp-client-probe.mjs) (`npm run probe:mcp-clients`) | Free remote MCP server for Grok Bot, Grok connectors and the xAI API: no call hangs, quota per MCP session or install token, OAuth 2.1 or a connector API key adds agent tools and never a spend tool. Connector reference: [docs/grok-bot.md](docs/grok-bot.md) `→ /docs/grok-bot`; product tour [docs/grok.md](docs/grok.md) |
| X creation claim | Page [pages/x-claim.html](pages/x-claim.html) `→ /x/claim` ([src/x-claim.js](src/x-claim.js)), API [api/x/claim.js](api/x/claim.js), logic [api/_lib/x-creation-claim.js](api/_lib/x-creation-claim.js), ledger migration [api/_lib/migrations/20261009213000_x_creation_claims.sql](api/_lib/migrations/20261009213000_x_creation_claims.sql) | Models the @-mention bot made for an X author move from the bot account into their library when they link the same X id (on link, on the page, or at creation time). Doc: [docs/x-mention-bot.md](docs/x-mention-bot.md). Tests: [tests/x-creation-claim.test.js](tests/x-creation-claim.test.js) |
| Awesome 3D Agents (curated list) | Source [data/awesome.json](data/awesome.json), generator [scripts/build-awesome.mjs](scripts/build-awesome.mjs) (`npm run build:awesome`, drift-gated by `npm run check:awesome`, publishable mirror via `npm run awesome:standalone`), outputs [awesome/README.md](awesome/README.md) + [public/awesome.json](public/awesome.json), page [pages/awesome.html](pages/awesome.html) `-> /awesome`, link checker [scripts/check-awesome-links.mjs](scripts/check-awesome-links.mjs) (`npm run awesome:links`) | Live | An awesome-list of everything needed to give an AI agent a body: text-to-3D, capture and splatting, avatars, rigging, motion, lipsync and voice, web renderers, asset pipelines, physics and networking, agent frameworks, datasets, free assets, learning. One JSON source produces both the GitHub-facing list and the searchable page, so they cannot disagree. Every url is fetched and classified (ok / moved / bot-filtered / broken) before it ships; the checker stays out of the deploy path so a third-party outage cannot redden someone else's build. The README is written to pass `npx awesome-lint`: badge on the heading line, no License section, no Contributing entry in the contents, and every description capitalised and ended with a period, all enforced by the generator and by [tests/awesome-list.test.js](tests/awesome-list.test.js). Its last two lint rules read GitHub repository topics, which a list inside a product repo cannot satisfy, so `--standalone` emits a ready-to-publish mirror repo (readme, contributing, code of conduct, license) outside this checkout. Contributing: [awesome/CONTRIBUTING.md](awesome/CONTRIBUTING.md) |
diff --git a/data/changelog.json b/data/changelog.json
index 005b0cf4f..28972d342 100644
--- a/data/changelog.json
+++ b/data/changelog.json
@@ -29593,6 +29593,13 @@
"summary": "three.ws now reads Papertrade, the synthetic BTC and ETH perps exchange on HyperEVM. Ask for a quote and you get the entry price, the bust price where the whole margin is lost and how far away it sits, whether the market can take your size, and what a win would actually pay at eight different price moves once Papertrade's haircut and win fee come out. Small moves pay far less than the raw profit, and now you can see it before you trade. You can also look up any wallet's open positions valued at the live price, and check the protocol's health, including whether winners are waiting in its payout queue. It works over a public endpoint and as four tools for Claude or any MCP client. It only reads: you still trade on Papertrade from your own wallet.",
"tags": ["feature"],
"link": "/docs/papertrade"
+ },
+ {
+ "date": "2026-10-10",
+ "title": "Every MCP tool now has its own page, and the tool counts are measured, not typed",
+ "summary": "The MCP tool catalog now shows the real totals for every server, worked out from the live servers with a plain note on how, and a release view that lists which tools each release added. Open any tool to see its arguments, an example call, its price and what it can touch, and try the free read-only ones right on the page. You can filter the catalog by category. Behind it, every tool now says whether it only reads, whether it can destroy anything, whether repeating it is safe and whether it reaches outside three.ws, and every tool says when to use it. Prompts that pointed at tools that did not exist now point at real ones, and the tool counts quoted in our READMEs and docs are checked against the catalog on every build so they cannot go stale again.",
+ "tags": ["feature", "improvement"],
+ "link": "/mcp-tools"
}
]
}
diff --git a/data/pages.json b/data/pages.json
index 2781636ad..b94a6ae5a 100644
--- a/data/pages.json
+++ b/data/pages.json
@@ -6039,7 +6039,7 @@
{
"path": "/mcp-tools",
"title": "MCP Tool Catalog",
- "description": "Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.",
+ "description": "Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.",
"priority": 0.8,
"changefreq": "weekly",
"added": "2026-07-30"
diff --git a/docs/api-reference.md b/docs/api-reference.md
index 0cda79f85..d49204401 100644
--- a/docs/api-reference.md
+++ b/docs/api-reference.md
@@ -217,6 +217,18 @@ The endpoint allows cross-origin `GET` and `POST` requests and requires no authe
---
+## MCP Census API
+
+### Count every MCP tool, resource and prompt
+
+`GET /api/mcp-census` (public, no auth, rate limited per IP) returns how many tools, resources, resource templates and prompts each three.ws MCP server serves. The hosted endpoints are counted by the running server from the same catalogs it answers `tools/list` from. The stdio npm packages cannot load inside the API runtime, so their rows come from the build's [`/tools.json`](https://three.ws/tools.json).
+
+```bash
+curl -s https://three.ws/api/mcp-census | jq '.totals.all, .matchesBuild'
+```
+
+Response fields: `totals` (`all`, `hosted`, `stdio`, each with `servers`, `tools`, `uniqueTools`, `resources`, `templates`, `prompts`), `servers` (one row per server with a `source` of `live` or `build`), `method` (how each number is calculated), `matchesBuild` (false when the build ran on different code than is serving) and `drift` (the per-server differences). Today the build counts <!-- mcp-count:all.tools -->631<!-- /mcp-count --> tools on <!-- mcp-count:all.servers -->51<!-- /mcp-count --> servers. Browse them at [/mcp-tools](https://three.ws/mcp-tools); see [MCP Tools Catalog](mcp-tools.md#how-the-totals-are-calculated) for the method.
+
## Asset Catalog API
One search across every ready-made asset three.ws publishes: the CC0 object/prop library, the ready-made character library, and the motion-clip library. **No authentication, no API key, no payment.** Open CORS, cached at the edge for 5 minutes.
diff --git a/docs/mcp-tools.md b/docs/mcp-tools.md
index d9fc95348..2a425394f 100644
--- a/docs/mcp-tools.md
+++ b/docs/mcp-tools.md
@@ -25,6 +25,24 @@ page explains how the servers are grouped and how the paid ones charge.
---
+## How the totals are calculated
+
+The totals are computed, never typed. At build time `npm run build:mcp-catalog` imports the exact catalog each hosted endpoint serves, and loads every stdio package in-process and asks it for `tools/list`, `resources/list` and `prompts/list` over an in-memory MCP transport. The result is [`/tools.json`](/tools.json) and [`/mcp-catalog.json`](/mcp-catalog.json), currently <!-- mcp-count:all.tools -->631<!-- /mcp-count --> tools (<!-- mcp-count:all.uniqueTools -->543<!-- /mcp-count --> unique names) on <!-- mcp-count:all.servers -->51<!-- /mcp-count --> servers. At request time [`/api/mcp-census`](/api/mcp-census) recounts the hosted endpoints from the running code and reports whether they still match the build.
+
+- **tools**: every tool a server can serve, including financial-tier tools the policy hides until a session enables them.
+- **resources, templates, prompts**: the matching `*/list` entries, prompts rendered against that server's own catalog.
+- **unique**: distinct tool names. `/api/mcp-chatgpt` and `/api/mcp-grok` serve subsets of `/api/mcp-studio`, so per-server figures overlap.
+
+Every tool declares all four annotations (`readOnlyHint`, `destructiveHint`, `idempotentHint`, `openWorldHint`) and a description with a "Use this when..." line; `tests/mcp-tool-quality.test.js` fails otherwise, and `tests/mcp-prompt-references.test.js` fails when a prompt names a tool, resource or prompt that does not exist. Run both with `npm run test:mcp-surface`.
+
+**Quoting a count in a doc.** Wrap it in a marker: `<!-- mcp-count:mcp-3d.tools -->40<!-- /mcp-count -->`. The key is `<scope>.<field>`: scope is `all`, `hosted`, `stdio` or a server id from `/tools.json`; field is `servers`, `tools`, `uniqueTools`, `resources`, `templates`, `prompts`, `free` or `paid`. `npm run check:mcp-counts` (part of `npm run gate`) fails on a marker that disagrees with the census and on an unmarked "N tools" in a living doc that is about a server; `npm run check:mcp-counts -- --fix` rewrites marker values. Add `<!-- mcp-count-ignore -->` to a line whose number is not about a three.ws server.
+
+## Per-tool pages and releases
+
+Every tool has a page at `/mcp-tools/<server>/<tool>` with its schema, an example call (curl, JSON-RPC body, client config), its price and hints. Free, read-only tools served over HTTP have a try-it form that calls the live endpoint. [`/mcp-tools#releases`](/mcp-tools#releases) shows which tools each release added, built from git history into [`/mcp-tool-history.json`](/mcp-tool-history.json).
+
+---
+
## How paid MCP tools charge
The paid servers follow the MCP v2 transport convention: a `tools/call` made
@@ -140,6 +158,7 @@ generation lane**; the rest are paid and quote their price in the
| Bazaar MCP | `api/mcp-bazaar.js` | x402 service discovery — see [x402 bazaar](mcp-x402-bazaar.md). |
| IBM MCP | `api/ibm-mcp.js` | watsonx / Granite integration — see [IBM](ibm.md). |
| pump.fun MCP | `api/pump-fun-mcp.js` | Launch/trade tools — see [Solana pump.fun](solana-pumpfun.md). |
+| Viewer Control | `api/chat/mcp.js` | Drives a live model viewer (wireframe, lighting, screenshots, load a model); tools in `api/_lib/viewer-mcp-tools.js`. |
## $THREE only
diff --git a/public/changelog-recent.json b/public/changelog-recent.json
index ba353a5d9..74879d303 100644
--- a/public/changelog-recent.json
+++ b/public/changelog-recent.json
@@ -1,11 +1,11 @@
{
- "generated_at": "2026-10-10T20:09:17.507Z",
+ "generated_at": "2026-10-10T20:39:45.789Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
"url": "https://three.ws"
},
- "total": 3932,
+ "total": 3933,
"complete": false,
"full_feed": "/changelog.json",
"entries": [
@@ -338,6 +338,17 @@
"docs"
]
},
+ {
+ "date": "2026-10-10",
+ "type": "update",
+ "title": "Every MCP tool now has its own page, and the tool counts are measured, not typed",
+ "summary": "The MCP tool catalog now shows the real totals for every server, worked out from the live servers with a plain note on how, and a release view that lists which tools each release added. Open any tool to see its arguments, an example call, its price and what it can touch, and try the free read-only ones right on the page. You can filter the catalog by category. Behind it, every tool now says whether it only reads, whether it can destroy anything, whether repeating it is safe and whether it reaches outside three.ws, and every tool says when to use it. Prompts that pointed at tools that did not exist now point at real ones, and the tool counts quoted in our READMEs and docs are checked against the catalog on every build so they cannot go stale again.",
+ "link": "/mcp-tools",
+ "tags": [
+ "feature",
+ "improvement"
+ ]
+ },
{
"date": "2026-10-10",
"type": "update",
@@ -1530,17 +1541,6 @@
"tags": [
"feature"
]
- },
- {
- "date": "2026-09-30",
- "type": "update",
- "title": "The language menu now offers 69 languages",
- "summary": "The language menu grew from 14 languages to 69, each one fully translated. 55 more pages now follow the language you pick, including Hood Desk, Portfolios, Fee Bridge, Agent Cards, Connect, the CLI sign-in approval, Motion, Docs World and the legal pages. Their titles, headings, buttons and the text shown when a page is shared all translate, and so does the sitemap, so you can find every page on three.ws in your own language.",
- "link": "/sitemap",
- "tags": [
- "feature",
- "improvement"
- ]
}
]
}
diff --git a/public/changelog.json b/public/changelog.json
index b7b3e3e6c..6dc2773d1 100644
--- a/public/changelog.json
+++ b/public/changelog.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-10-10T20:09:17.485Z",
+ "generated_at": "2026-10-10T20:39:45.768Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json + data/changelog.json",
"site": {
"name": "three.ws",
@@ -335,6 +335,17 @@
"docs"
]
},
+ {
+ "date": "2026-10-10",
+ "type": "update",
+ "title": "Every MCP tool now has its own page, and the tool counts are measured, not typed",
+ "summary": "The MCP tool catalog now shows the real totals for every server, worked out from the live servers with a plain note on how, and a release view that lists which tools each release added. Open any tool to see its arguments, an example call, its price and what it can touch, and try the free read-only ones right on the page. You can filter the catalog by category. Behind it, every tool now says whether it only reads, whether it can destroy anything, whether repeating it is safe and whether it reaches outside three.ws, and every tool says when to use it. Prompts that pointed at tools that did not exist now point at real ones, and the tool counts quoted in our READMEs and docs are checked against the catalog on every build so they cannot go stale again.",
+ "link": "/mcp-tools",
+ "tags": [
+ "feature",
+ "improvement"
+ ]
+ },
{
"date": "2026-10-10",
"type": "update",
@@ -16597,7 +16608,7 @@
"date": "2026-07-30",
"type": "launch",
"title": "MCP Tool Catalog",
- "summary": "Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.",
+ "summary": "Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.",
"link": "/mcp-tools",
"tags": [
"launch"
diff --git a/public/changelog.xml b/public/changelog.xml
index 8797b4508..ffdd4ecfc 100644
--- a/public/changelog.xml
+++ b/public/changelog.xml
@@ -262,6 +262,14 @@
<category>feature</category>
<description>Every API key now sits on a developer plan: Free, Builder, Scale or Enterprise, each with a monthly call quota, a per-minute burst ceiling, a concurrency ceiling and a webhook cap, all enforced on every /api/v1 call rather than only recorded. Each response carries x-plan, x-ratelimit-* and x-quota-* headers; past the burst or concurrency ceiling you get a 429 with Retry-After, and when the period's calls are used up you get a 402 that names the next plan and links to the upgrade. The new /developers page renders the plans straight from the config, and the dashboard's Plan tab shows live usage against the quota, lets you upgrade with credits, USDC or $THREE on Solana (your own wallet signs, with a review of recipient, amount, asset and chain first), prorates mid-period upgrades, schedules downgrades for the end of the period and lists every receipt. Revoking a key now takes effect immediately on every server. Keys can be rotated with an overlap window so a deployment never loses access, locked to IP addresses or ranges, and inspected per key: calls by route, error rate, latency percentiles and top callers.</description>
</item>
+ <item>
+ <title>Every MCP tool now has its own page, and the tool counts are measured, not typed</title>
+ <link>https://three.ws/mcp-tools</link>
+ <guid isPermaLink="false">2026-10-10:Every MCP tool now has its own page, and the tool counts are measured, not typed</guid>
+ <pubDate>Sat, 10 Oct 2026 12:00:00 GMT</pubDate>
+ <category>feature</category>
+ <description>The MCP tool catalog now shows the real totals for every server, worked out from the live servers with a plain note on how, and a release view that lists which tools each release added. Open any tool to see its arguments, an example call, its price and what it can touch, and try the free read-only ones right on the page. You can filter the catalog by category. Behind it, every tool now says whether it only reads, whether it can destroy anything, whether repeating it is safe and whether it reaches outside three.ws, and every tool says when to use it. Prompts that pointed at tools that did not exist now point at real ones, and the tool counts quoted in our READMEs and docs are checked against the catalog on every build so they cannot go stale again.</description>
+ </item>
<item>
<title>Import skills from any registry, safely</title>
<link>https://three.ws/skills/import</link>
@@ -12524,7 +12532,7 @@ And all of it is public. Oracle Lab publishes the actual model: every weight, th
<guid isPermaLink="false">2026-07-30:MCP Tool Catalog</guid>
<pubDate>Thu, 30 Jul 2026 12:00:00 GMT</pubDate>
<category>launch</category>
- <description>Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.</description>
+ <description>Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.</description>
</item>
<item>
<title>Recipe: build a whole asset pack in parallel</title>
diff --git a/public/features.json b/public/features.json
index cec91cc5a..e8794f5e0 100644
--- a/public/features.json
+++ b/public/features.json
@@ -1,5 +1,5 @@
{
- "generated_at": "2026-10-10T20:09:17.474Z",
+ "generated_at": "2026-10-10T20:39:45.757Z",
"generated_by": "scripts/build-page-index.mjs from data/pages.json",
"site": {
"name": "three.ws",
@@ -7833,7 +7833,7 @@
{
"path": "/mcp-tools",
"title": "MCP Tool Catalog",
- "description": "Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.",
+ "description": "Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.",
"added": "2026-07-30",
"auth": null,
"indexable": true,
diff --git a/public/llms-full.txt b/public/llms-full.txt
index e8092ba92..594e8d2fa 100644
--- a/public/llms-full.txt
+++ b/public/llms-full.txt
@@ -4714,7 +4714,7 @@ Add three.ws to your AI client in two clicks: one connector URL gives Claude, Ch
URL: https://three.ws/mcp-tools
-Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.
+Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.
### Docs · The 10 SOL trading experiment
diff --git a/public/llms.txt b/public/llms.txt
index 69f9074ad..40e161aea 100644
--- a/public/llms.txt
+++ b/public/llms.txt
@@ -59,7 +59,7 @@ Machine-readable entry points. Fetch these instead of scraping HTML.
- [Connect three.ws to Claude, ChatGPT, Cursor & VS Code](https://three.ws/connect): Add three.ws to your AI client in two clicks: one connector URL gives Claude, ChatGPT, Cursor, VS Code or Claude Code the three.ws MCP tools for 3D generation, agents, wallets and x402 payments. Sign in once in your browser, with no API key to copy.
- [three.ws for Grok](https://three.ws/grok): One sentence gives Grok Bot a 3D studio. Text and images become textured 3D models, rigged avatars, and a talking 3D body Grok can wear. Works in Grok Bot, Grok connectors and the xAI API. Free, no account, no key.
-- [MCP Tool Catalog](https://three.ws/mcp-tools): Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.
+- [MCP Tool Catalog](https://three.ws/mcp-tools): Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.
- [Docs · Start Here](https://three.ws/docs/start-here): Plain-language introduction to three.ws for creators and non-developers: what it is, who it’s for, and where to begin.
- [Docs · MCP](https://three.ws/docs/mcp): Expose your agent as an MCP server for Claude, ChatGPT, and other clients.
- [Docs · three-ws CLI](https://three.ws/docs/cli): Connect Claude Code, Claude Desktop, Cursor, Windsurf, VS Code, Codex, Gemini CLI or Hermes to three.ws in one command: npx three-ws setup signs you in, writes every client's MCP config and verifies each server with a live tools/list.
diff --git a/public/mcp-tool-history.json b/public/mcp-tool-history.json
index 3d1583f67..b6fae9099 100644
--- a/public/mcp-tool-history.json
+++ b/public/mcp-tool-history.json
@@ -792,6 +792,10 @@
"offer_list",
"order_book",
"order_preview",
+ "papertrade_account",
+ "papertrade_markets",
+ "papertrade_protocol",
+ "papertrade_quote",
"perps_account",
"perps_action_preview",
"perps_collateral_deposit",
@@ -984,9 +988,9 @@
},
"removed": {},
"counts": {
- "added": 258,
+ "added": 262,
"removed": 0,
- "total": 631
+ "total": 635
}
}
]
diff --git a/public/sitemap/index.html b/public/sitemap/index.html
index 1aeb7e8ff..d80bf83f5 100644
--- a/public/sitemap/index.html
+++ b/public/sitemap/index.html
@@ -5643,7 +5643,7 @@
<a href="/mcp-tools">
<span class="sm-title"><span data-i18n="sitemap_index.t_mcp_tools">MCP Tool Catalog</span></span>
<span class="sm-path" translate="no">/mcp-tools</span>
- <span class="sm-desc" data-i18n="sitemap_index.d_mcp_tools">Every MCP tool three.ws publishes, searchable in one place: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Generated from the source of each tool, so it never drifts from what the servers serve.</span>
+ <span class="sm-desc" data-i18n="sitemap_index.d_mcp_tools">Every MCP tool three.ws publishes, searchable and filterable by category: what it does, which server hosts it, what it costs in USDC, and whether an AI client can run it unattended. Open any tool for its schema, an example call and a try-it for the free read-only ones. Totals are computed from the live servers, with a note on how, and a release diff shows which tools were added when.</span>
</a>
</li>
<li>
diff --git a/public/tools.json b/public/tools.json
index fa83354de..1b30cfff9 100644
--- a/public/tools.json
+++ b/public/tools.json
@@ -6,8 +6,8 @@
"totals": {
"all": {
"servers": 51,
- "tools": 631,
- "uniqueTools": 543,
+ "tools": 635,
+ "uniqueTools": 547,
"resources": 24,
"uniqueResources": 11,
"templates": 21,
@@ -17,8 +17,8 @@
},
"hosted": {
"servers": 10,
- "tools": 367,
- "uniqueTools": 324,
+ "tools": 371,
+ "uniqueTools": 328,
"resources": 22,
"uniqueResources": 9,
"templates": 21,
@@ -58,9 +58,9 @@
"title": "Agent Wallet",
"endpoint": "/api/mcp-agent",
"transport": "remote",
- "tools": 100,
- "defaultOn": 74,
- "readOnly": 45,
+ "tools": 104,
+ "defaultOn": 78,
+ "readOnly": 49,
"destructive": 26,
"resources": 6,
"templates": 9,
@@ -2636,6 +2636,46 @@
"whenToUse": "Use this when the owner wants to reduce an agent's perps risk or be alerted before a position gets into trouble.",
"page": "https://three.ws/mcp-tools/mcp-agent/perps_limits"
},
+ {
+ "name": "papertrade_markets",
+ "server": "mcp-agent",
+ "title": "List Papertrade markets",
+ "category": "perps",
+ "safety": "read",
+ "price": 0,
+ "whenToUse": "Call this first to see what can be traded.",
+ "page": "https://three.ws/mcp-tools/mcp-agent/papertrade_markets"
+ },
+ {
+ "name": "papertrade_quote",
+ "server": "mcp-agent",
+ "title": "Quote a Papertrade position",
+ "category": "perps",
+ "safety": "read",
+ "price": 0,
+ "whenToUse": null,
+ "page": "https://three.ws/mcp-tools/mcp-agent/papertrade_quote"
+ },
+ {
+ "name": "papertrade_account",
+ "server": "mcp-agent",
+ "title": "Read a Papertrade wallet",
+ "category": "perps",
+ "safety": "read",
+ "price": 0,
+ "whenToUse": null,
+ "page": "https://three.ws/mcp-tools/mcp-agent/papertrade_account"
+ },
+ {
+ "name": "papertrade_protocol",
+ "server": "mcp-agent",
+ "title": "Check Papertrade protocol health",
+ "category": "perps",
+ "safety": "read",
+ "price": 0,
+ "whenToUse": null,
+ "page": "https://three.ws/mcp-tools/mcp-agent/papertrade_protocol"
+ },
{
"name": "token_search",
"server": "mcp-agent",
@@ -4303,7 +4343,7 @@
"category": "launch",
"safety": "write",
"price": 0,
- "whenToUse": "Call this before launching a coin, pass the returned uri to the launch-agent endpoint or the studio launch flow.",
+ "whenToUse": "Call this before launching a coin — pass the returned uri to the launch-agent endpoint or the studio launch flow.",
"page": "https://three.ws/mcp-tools/pump-fun-mcp/pumpfun_upload_metadata"
},
{
@@ -4489,7 +4529,7 @@
{
"name": "restyle_material",
"server": "three-ws-mcp-server",
- "title": "Restyle a 3D model’s materials, AI PBR restyle or seeded colorway variants",
+ "title": "Restyle a 3D model’s materials — AI PBR restyle or seeded colorway variants",
"category": "utility",
"safety": "write",
"price": 0.05,
@@ -4519,7 +4559,7 @@
{
"name": "agent_hire_discover",
"server": "three-ws-mcp-server",
- "title": "Agent hire, discover ($0.01)",
+ "title": "Agent hire — discover ($0.01)",
"category": "utility",
"safety": "read",
"price": 0.01,
@@ -4723,7 +4763,7 @@
"category": "intelligence",
"safety": "read",
"price": 0,
- "whenToUse": "Use it for situational awareness, what agents, coins, and players are active right now.",
+ "whenToUse": "Use it for situational awareness — what agents, coins, and players are active right now.",
"page": "https://three.ws/mcp-tools/activity-mcp/get_feed_events"
},
{
@@ -4753,7 +4793,7 @@
"category": "agents",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to verify another agent before coordinating with it, confirm it is registered, active, and what it claims to do.",
+ "whenToUse": "Use this to verify another agent before coordinating with it — confirm it is registered, active, and what it claims to do.",
"page": "https://three.ws/mcp-tools/agenc-mcp/get_agent"
},
{
@@ -4773,7 +4813,7 @@
"category": "x402",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to discover paid work an agent can earn by calling, the x402 complement to the on-chain task marketplace.",
+ "whenToUse": "Use this to discover paid work an agent can earn by calling — the x402 complement to the on-chain task marketplace.",
"page": "https://three.ws/mcp-tools/agenc-mcp/query_x402_services"
},
{
@@ -4993,7 +5033,7 @@
"category": "intelligence",
"safety": "read",
"price": 0,
- "whenToUse": "Use this to review what fired; pair it with list_alert_rules, whose `recent_deliveries` shows per-channel send outcomes, to see both what fired and how it was delivered.",
+ "whenToUse": "Use this to review what fired; pair it with list_alert_rules, whose `recent_deliveries` shows per-channel send outcomes — to see both what fired and how it was delivered.",
"page": "https://three.ws/mcp-tools/alerts-mcp/get_alert_history"
},
{