Set up LibreChat
Self-hosted AI chat platform (35K+ GitHub stars) with the most complete MCP transport support. Add Agentcy via YAML config for marketing intelligence.
- 01
Sign up at app.goagentcy.com and create an API key
- 02
Edit your librechat.yaml config file (mounted at /app/librechat.yaml in Docker)
- 03
Add the mcpServers section as shown below
- 04
Replace YOUR_AGENTCY_API_KEY with your actual key
- 05
Restart LibreChat (docker compose restart api) to load the new config
path: librechat.yaml
mcpServers:
agentcy:
type: streamable-http
url: https://data.goagentcy.com/mcp
headers:
Authorization: "Bearer YOUR_AGENTCY_API_KEY"
timeout: 30000
initTimeout: 10000Requires LibreChat v0.8.0-rc1+ for the streamable-http transport. LibreChat has built-in SSRF protection — public HTTPS domains (like ours) work by default. Only add mcpSettings.allowedDomains if you're running an internal MCP server on a private IP; adding it turns it into a restrictive allowlist that will block your other MCP servers. Supports ${ENV_VAR} interpolation in headers. Restart required after config changes.
Stuck or want to verify these instructions yourself? These are the documentation sources we used. If something here doesn't match what you see in your client, the vendor may have updated their UI — and we'll get this page updated.
After connecting LibreChat and configuring your data sources in the portal, ask questions about any of them in natural language: