Skip to content

The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu

docs: document Beacon Cloud MCP finding tools

Claude89ebccafd96f
diff --git a/docs/cli/mcp-connect.mdx b/docs/cli/mcp-connect.mdx
index e3f4436e..02ece94a 100644
--- a/docs/cli/mcp-connect.mdx
+++ b/docs/cli/mcp-connect.mdx
@@ -26,8 +26,10 @@ with different names, so neither entry ever overwrites the other:
| `beacon-managed` | Session history this endpoint forwarded to Beacon Cloud | Beacon Cloud, over HTTPS | `beacon mcp connect` |
Beacon Cloud MCP reads your forwarded history with `beacon_search_sessions`, `beacon_grep`,
-`beacon_read_session`, `beacon_get_event`, `beacon_lookup` and `beacon_usage`. A connection
-signed in with write access can also publish lenses; see [Beacon Cloud MCP](/deployment/managed-mcp#tools).
+`beacon_read_session`, `beacon_get_event`, `beacon_lookup` and `beacon_usage`, and your Beacon
+Cloud findings with `beacon_findings_list` and `beacon_get_finding`. A connection signed in with
+write access can also share sessions, publish lenses and give feedback on findings; see
+[Beacon Cloud MCP](/deployment/managed-mcp#tools).
Tokens from `beacon mcp token create` are always read-only.
<Note>
diff --git a/docs/deployment/managed-mcp.mdx b/docs/deployment/managed-mcp.mdx
index 34cd30dc..f51d672e 100644
--- a/docs/deployment/managed-mcp.mdx
+++ b/docs/deployment/managed-mcp.mdx
@@ -110,10 +110,11 @@ List my five most recent Beacon sessions.
When your client signs in, the Beacon approval page asks what to allow:
-- **Read** is always granted. The agent can search and read your sessions: prompts, responses,
- tool calls and output, commands and file edits.
+- **Read** is always granted. The agent can search and read your sessions (prompts, responses,
+ tool calls and output, commands and file edits) and your findings.
- **Write** is optional and only offered when the client asks for it. Tick the checkbox to let the
- agent create, upload, release and publish lenses under your account.
+ agent share your sessions, create, upload, release and publish lenses under your account, and
+ record your feedback on findings or resolve and dismiss them.
Neither lets the agent change your sessions, your devices, or anything on your machine, or read
anyone else's data. A tool that needs write access is hidden from read-only connections.
@@ -130,12 +131,22 @@ anyone else's data. A tool that needs write access is hidden from read-only conn
| `beacon_usage` | Summarizes token usage and reported cost by model, harness, repository or day |
| `beacon_lenses_list` | Lists your lenses, the lenses you added, or the marketplace |
| `beacon_lenses_*` | Create, upload, release and update lenses (write access). See [Lenses with MCP](/cloud/lenses/lenses-mcp) |
+| `beacon_findings_list` | Lists your findings, the ones that still need review first, filtered by severity or kind |
+| `beacon_get_finding` | Returns one finding in full: detail, recommendation, cited sessions and evidence, and the prompt in effect |
+| `beacon_finding_feedback` | Marks a finding helpful or not helpful with a note, and/or sets it resolved, dismissed or open (write access) |
Time filters accept a relative window such as `24h`, `7d` or `2w`, or exact `after` and `before`
dates. `beacon_read_session` also accepts a dashboard session URL.
Agents work best when they search first and then read only the part of a session they need.
+Findings are what Beacon Cloud's hourly analysis noticed in your forwarded activity (security
+issues, repeated workflows worth turning into skills, and behavioral insights), the same ones the
+dashboard's **Findings** page shows. They are separate from the local `beacon scan` results.
+Feedback and status set over MCP are the same review you give on the dashboard: the next analysis
+reads your feedback and note, so it stops repeating what you rejected. `beacon_get_finding` and
+`beacon_finding_feedback` also accept a finding's dashboard URL.
+
## Example prompts
- "Find the session where I fixed the release workflow last week."
@@ -143,6 +154,8 @@ Agents work best when they search first and then read only the part of a session
- "Search my Claude Code and Cursor history for changes to the MCP connection flow."
- "Summarize token usage for this repository over the past seven days, by model."
- "Build a lens that shows every failed command and publish it." (needs write access)
+- "Which of my Beacon findings are high severity? Open the first one and check its evidence."
+- "Dismiss that finding as not helpful: the key it flagged is a test fixture." (needs write access)
Session titles and summaries are metadata. For exact claims about commands, files or errors, have
the agent read the events.