Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.usesynth.ai/llms.txt

Use this file to discover all available pages before exploring further.

This page is the shortest path from zero to a working MCP connection. For product context first, read Introduction. For deeper MCP run patterns, use MCP Quickstart. For Python, use Python SDK Quickstart.

​
1. Sign in and API key

  1. Create or open your Synth account at usesynth.ai.
  2. Create a Synth API key in the product (same key type as other Synth API access).
  3. Expose it to your terminal and MCP clients as SYNTH_API_KEY.
For self-hosted or staging backends, set SYNTH_BACKEND_URL to that base URL. Production MCP defaults to the hosted API; see MCP Quickstart for details.

​
2. Install the Managed Research MCP

Managed Research MCP is published with the managed-research PyPI package (managed-research-mcp entry point). Most people connect through a remote HTTP server from Codex or Claude Code. 
codex mcp add managed-research --url https://api.usesynth.ai/mcp
Ensure SYNTH_API_KEY is available in the environment Codex uses (shell profile, IDE env, or Codex config), per Codex docs for MCP env inheritance.

​
3. Smoke test

In your agent client, ask for something that forces a tool call, for example: 
List my Managed Research projects.
You should see a call to smr_list_projects. An empty list still means auth and connectivity succeeded.

​
4. Next steps

Projects in the web app

Navigate the logged-in project hub, runs, resources, and results in the browser.

MCP Quickstart

Start one-off and project-scoped runs and inspect evidence from MCP.

MCP tool reference

Full smr_* tool list grouped by area.

Python SDK quickstart

Script runs, CI, and notebooks with ManagedResearchClient.
Public automation should use MCP or the managed-research Python package, not ad hoc /smr REST calls. See Introduction.