Mintlify hosts a search MCP server for Phinite Docs. When you connect it to an AI tool, the assistant can search and read this documentation while answering questions — instead of relying on generic web search or outdated training data.
On any docs page, open the contextual menu in the header and choose Connect to Cursor, Connect to VS Code, Copy MCP server URL, or Copy MCP install command for one-click setup.

​
MCP server URL

This endpoint is public and searches all indexed public documentation pages.

​
What you get

The MCP server exposes two tools: Agents also discover the auto-generated skill.md as an MCP resource, which summarizes what you can build with Phinite (assistants, Graph Studio, DevStudio, triggers, builds, and observability).

​
Connect in Cursor

1

Open MCP settings

Press Command + Shift + P (Ctrl + Shift + P on Windows), search for Open MCP settings, then click Add custom MCP.
2

Add the Phinite Docs server

In mcp.json, add:
3

Verify

In Cursor chat, ask a Phinite-specific question (for example, “How do I publish an agent graph?”). Cursor should search Phinite Docs and cite the relevant pages.

​
Connect in VS Code

Create or edit .vscode/mcp.json in your project:
See the VS Code MCP documentation for details.

​
Connect in Claude

1

Add a custom connector

Open Claude Connectors, click Add custom connector, and enter:
  • Name: Phinite Docs
  • URL: https://docs.phinite.ai/docs/mcp
2

Use in chat

Click the attachments button (+), select Phinite Docs, then ask your question.

​
Connect in Claude Code

Verify with:

​
Install as a skill

To add Phinite capabilities to an agent’s context without MCP, run:
This installs the hosted skill.md so agents know when and how to use Phinite.

​
Discovery endpoint

Agents can auto-discover the MCP server at:
The response includes the public server URL and transport details.
Phinite Docs is deployed under the /docs path. Use https://docs.phinite.ai/docs/mcp, not the site root.