The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
{
"zapier": {
"sse_url": "https://mcp.zapier.com/api/mcp"
},
"deepwiki": {
"http_url": "https://mcp.deepwiki.com/mcp",
"sse_url": "https://mcp.deepwiki.com/sse",
"description": "The DeepWiki MCP server provides programmatic access to DeepWiki's repository documentation (Devin Wiki) and search capabilities (Devin Search)."
},
"jira": {
"sse_url": "https://mcp.atlassian.com/v1/sse",
"description": "The Jira MCP server provides programmatic access to Jira's issue tracking capabilities."
},
"linear": {
"sse_url": "https://mcp.linear.app/sse",
"description": "The Linear MCP server provides programmatic access to Linear's issue tracking capabilities."
},
"scrapegraph": {
"http_url": "https://smithery.ai/api/mcp/scrapegraph-mcp",
"sse_url": "https://smithery.ai/api/mcp/scrapegraph-mcp/sse",
"description": "The ScrapeGraph MCP server provides programmatic access to ScrapeGraph AI's web scraping capabilities, including smart scraping, web crawling, search scraping, and agentic scraping workflows."
}
}