Sentrial provides an MCP (Model Context Protocol) server that lets AI coding tools search our documentation directly. Ask your AI to “instrument my agent with Sentrial” and it will pull the right docs, code examples, and API references automatically.Documentation Index
Fetch the complete documentation index at: https://www.sentrial.com/docs/llms.txt
Use this file to discover all available pages before exploring further.
Install with Claude Code
Run this in your terminal:SearchSentrial tool is now available in all your Claude Code sessions.
Install with Cursor
- Open Cursor Settings (
Cmd + ,/Ctrl + ,) - Go to the MCP section
- Click Add new MCP server
- Set the type to SSE and the URL to:
.cursor/mcp.json in your project:
What You Can Do
Once connected, just ask your AI assistant naturally:- “Instrument my agent with Sentrial”
- “Add Sentrial tracking to my LangChain agent”
- “How do I track tool calls with the Python SDK?”
- “Set up Sentrial with the Vercel AI SDK”
MCP Prompt Tips
For Claude Agent SDK integrations, include your language and runtime behavior in the prompt so the assistant returns the correct pattern:- “Set up Claude Code Python tracking with
wrap_claude_agent(forquery()) orwrap_claude_client(forClaudeSDKClient), and make sure sessions finalize with tokens/cost.” - “For Claude Code TypeScript, ensure early stream exits are handled so sessions don’t stay
running.” - “Show me the error-handling pattern for Claude Code wrappers, including generator-close behavior.”
- “I’m using
ClaudeSDKClientfor multi-turn conversations — show me how to track each turn as a Sentrial session withwrap_claude_client.”
How It Works
The MCP server exposes a singleSearchSentrial tool. When your AI assistant needs information about Sentrial, it calls this tool with a search query and gets back relevant documentation with code examples, API references, and direct links.
No API key is needed — the docs MCP is public and read-only.
