Skip to main content
Connect the Enrichley MCP server to your AI assistant in a couple of minutes. You will need an Enrichley account on a paid plan.

Prerequisites

  • An Enrichley paid plan (sign up).
  • An AI client that supports remote MCP servers with OAuth (Claude, Claude Code, Cursor, VS Code, or Codex).

MCP endpoint

Use this URL wherever your client asks for the MCP server URL:

Client setup

Add Enrichley as a custom connector to use it in Claude chats on the web, in the desktop app, and on mobile.
1

Open connector settings

In Claude, go to Settings → Connectors and click Add custom connector.
2

Name it and paste the URL

Name: Enrichley. URL: https://mcp.enrichley.io/mcp. Click Add.
3

Connect and sign in

Click Connect on the new connector. Your browser goes through Enrichley sign-in — use the same account you use at app.enrichley.io — and an authorization screen listing the requested scopes. Click Allow, then Authorize Claude.
4

Check the tools

Back in connector settings you should see Enrichley’s tools listed, grouped by permission. Paid actions default to Needs approval, so Claude asks before starting anything that spends credits.
Claude renders Enrichley’s interactive cards: your account status, preview tables, run quotes you can adjust and confirm yourself, and a download handoff with an Open in Enrichley button.
Complete the sign-in promptly after clicking Connect — the authorization attempt expires after a few minutes, and Claude will ask you to restart the connection.
On Claude Team and Enterprise plans, an Owner must first add the connector in Organization settings; members then connect it under Settings → Connectors with their own Enrichley sign-in.
Need to test the server outside of an AI client? See Debugging with MCP Inspector.

More clients

Beyond the clients above, the Enrichley MCP server has been validated against these additional MCP-compatible clients. Pick your client below for setup details.
Amazon Q Developer CLI supports remote HTTP MCP servers with OAuth.Config file: ~/.aws/amazonq/mcp.json (global) or .amazonq/mcp.json (workspace)
After saving, start a Q CLI session with an agent that includes this server. Run /mcp — Q CLI will mark the server as “not yet loaded” and provide an authorization URL. Open it in your browser, sign in to Enrichley, and authorize the requested scopes.
Cline supports remote HTTP MCP servers via the streamableHttp transport, including OAuth.Open the Cline panel → ConfigureConfigure MCP Servers, and add:
On first connect, Cline displays an OAuth URL in VS Code. Click it to complete sign-in in your browser. Cline stores credentials securely and reconnects automatically when you reload.
Gemini CLI supports remote HTTP MCP servers with OAuth via auto-discovery.Config file: ~/.gemini/settings.json (user) or .gemini/settings.json (project)
Gemini CLI auto-detects HTTP transport, falls back to SSE if needed, and discovers the OAuth flow from the server’s protected-resource metadata. On first use it opens your browser for sign-in.
JetBrains AI Assistant supports remote MCP servers with OAuth 2.1 + PKCE in version 2025.2 and newer.Open Settings → Tools → AI Assistant → Model Context Protocol (MCP) and add a new server, or edit the JSON config directly:
When you first invoke an Enrichley tool, the IDE opens your browser to complete the OAuth flow. Tokens are stored and refreshed automatically.
Requires AI Assistant 2025.2 or newer for full OAuth + Streamable HTTP support.
Roo Code’s native streamable-http transport does not yet trigger OAuth flows reliably on a 401 challenge (tracked in Issue #8119). Until that ships, use mcp-remote as a local stdio bridge — it handles OAuth on Roo Code’s behalf.Open Roo Code’s MCP settings and add:
mcp-remote opens your browser for OAuth on first run and caches tokens locally. Once Roo Code adds native OAuth 2.1 support, you can switch to a direct HTTP config.
Zed supports remote HTTP MCP servers with OAuth. Note that Zed uses context_servers in its config (not mcpServers).Open Zed’s settings (Cmd+, on macOS) and add:
When no Authorization header is configured, Zed initiates the standard MCP OAuth flow on first use.
There are open reports of Zed’s OAuth flow not always triggering reliably (Issue #43162). If you hit this, fall back to mcp-remote as a stdio bridge.

Not currently supported

GitHub Copilot Coding Agent cannot be used with the Enrichley MCP server. Per GitHub’s documentation, the Copilot cloud agent does not support remote MCP servers that use OAuth for authentication. We will revisit this when GitHub adds OAuth support.

Other MCP-compatible clients

The Enrichley MCP server works with any client that implements Streamable HTTP transport with OAuth 2.1 + PKCE. If your client meets that bar, point it at:
Static-API-key client configurations (using a header field like x-api-key) are not supported. The Enrichley MCP server requires OAuth.
If you get it working with a client we haven’t documented, let us know at support@enrichley.io and we’ll add it.

Verify the connection

Ask your AI assistant:
“Check my Enrichley credit balance.”
Your assistant should call the enrichley_get_account_status tool and return your available credits — in Claude, it renders as a card with a Refresh button. This call is free. If it works, you’re done. If not, see Troubleshooting.

Next steps

Tools Reference

See what each tool returns and how credits are counted.

Authentication

Learn how authorization works and how to disconnect.