Connect ELDRICK to your AI assistant

ChatGPT Plus, Pro, Business, Enterprise and Edu

1. Add ELDRICK by URL: go to chatgpt.com/plugins, choose + → Add custom MCP server, paste https://api.eldrick.com/mcp, pick OAuth, then Create as a plugin.
2. Sign in with your ELDRICK account. A new email gets an account on the spot, with a 6-digit code.
3. Ask for a fitting: “Fit me for a driver. I’m right-handed and swing about 98 mph.”

ELDRICK’s listing in the ChatGPT Plugin Directory is in review. Once it’s listed, search the directory for ELDRICK and choose Connect. Your workspace policy may need to allow custom MCP servers.

Claude claude.ai, Claude Desktop and mobile (Pro, Max, Team, Enterprise)

1. Open Settings → Connectors and choose Add custom connector. Once ELDRICK is listed, pick it from Browse connectors instead.
2. Name it ELDRICK and paste https://api.eldrick.com/mcp.
3. Choose Connect and sign in with your ELDRICK account. On Team and Enterprise plans an owner adds the connector first.

ELDRICK’s listing in the Claude connector directory is in review, so add it by URL for now.

Claude Code terminal

1. Run claude mcp add --transport http eldrick https://api.eldrick.com/mcp.
2. Inside Claude Code, run /mcp, pick eldrick and sign in. The browser returns you to the terminal.

Microsoft Copilot Microsoft 365 Copilot and Copilot Studio

1. Microsoft 365 Copilot: once published, find ELDRICK in the Agent Store, or ask your Microsoft 365 admin to deploy it from Integrated apps.
2. Copilot Studio: in your agent, open Tools → Add a tool → New tool → Model Context Protocol, paste https://api.eldrick.com/mcp then choose OAuth 2.0 → Dynamic discovery and Create.
3. Sign in with your ELDRICK account when Copilot asks.

Your organization needs a pre-registered client ID and secret for its tenant? Email api@eldrick.com.

Gemini the Gemini app, Gemini CLI and Gemini Enterprise

1. Gemini app (web first, then mobile): Settings → Connected apps → Add a custom app, paste https://api.eldrick.com/mcp and sign in. Google limits this to personal accounts, 18+, in the US, in English.
2. Gemini CLI: gemini mcp add --transport http eldrick https://api.eldrick.com/mcp, then /mcp auth eldrick inside Gemini CLI.
3. Gemini Enterprise: an admin adds a custom MCP server data store with the URL above and an ELDRICK client ID and secret (email api@eldrick.com for one).

Perplexity Pro, Max and Enterprise

1. Open Account Settings → Connectors, choose + Custom connector, then Remote.
2. Name it ELDRICK, paste https://api.eldrick.com/mcp and choose OAuth 2.0. Perplexity finds the sign-in settings on its own.
3. Sign in with your ELDRICK account, then turn the connector on in a thread.

Le Chat (Mistral) admins on Team and Enterprise, the account owner on Free and Pro

1. Open Connectors, choose + Add Connector and the Custom MCP Connector tab.
2. Name it ELDRICK and paste https://api.eldrick.com/mcp. Le Chat detects OAuth.
3. Choose Connect. Each member then signs in with their own ELDRICK account.

Meta Muse muse.ai, the Muse apps and WhatsApp (US)

1. Open Settings → Connectors and choose Add custom connector.
2. Paste https://api.eldrick.com/mcp and sign in with your ELDRICK account.
3. Ask Muse for a fitting. Muse asks you to approve each ELDRICK tool the first time it runs.

ELDRICK isn’t in the Muse connector directory yet, so add it by URL.

Grok grok.com and the Grok apps, all plans

1. Go to grok.com/connectors and choose New Connector → Custom.
2. Paste https://api.eldrick.com/mcp and sign in with your ELDRICK account.
3. Ask Grok for a fitting: “Fit me for irons. I’m left-handed and my 7-iron speed is about 80 mph.”

ELDRICK isn’t in Grok’s connector catalog, so add it as a custom connector. On Grok Business and Enterprise, an admin adds it first at console.x.ai (Grok Business → Connectors → + Add Connector → Other).

Grok (developers) xAI API: the Responses API and the xai-sdk

1. Get an ELDRICK developer key (eld_...) from the dashboard and an xAI key from console.x.ai. Keep both in environment variables, never in code or prompts.
2. Attach ELDRICK as a remote MCP tool. xAI connects to it and calls its tools for you. Python, with pip install xai-sdk:

   import os
   from xai_sdk import Client
   from xai_sdk.chat import user
   from xai_sdk.tools import mcp
   
   client = Client(api_key=os.environ["XAI_API_KEY"])
   chat = client.chat.create(
       model="grok-4.7",
       tools=[mcp(
           server_url="https://api.eldrick.com/mcp",
           server_label="eldrick",
           authorization=os.environ["ELDRICK_API_KEY"],
           extra_headers={"X-ELDRICK-Platform": "grok"},
       )],
   )
   chat.append(user("Fit me for a driver. Right-handed, 98 mph, I slice it."))
   print(chat.sample().content)

3. Or the OpenAI-compatible Responses API (https://api.x.ai/v1/responses):

   curl https://api.x.ai/v1/responses \
     -H "Authorization: Bearer $XAI_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
     "model": "grok-4.7",
     "input": [{"role": "user", "content": "Fit me for a driver. Right-handed, 98 mph, I slice it."}],
     "tools": [{
       "type": "mcp",
       "server_url": "https://api.eldrick.com/mcp",
       "server_label": "eldrick",
       "authorization": "'"$ELDRICK_API_KEY"'",
       "headers": {"X-ELDRICK-Platform": "grok"}
     }]
   }'

4. In your system prompt, have Grok ask which club, right- or left-handed, swing speed with that club, and the usual miss, then call analyze_fitting once with an idempotencyKey. If it returns status running, poll get_fitting. Show the specs and top picks with “Fit by ELDRICK”.

xAI sends authorization to ELDRICK in the Authorization header (with or without Bearer , both work). allowed_tools limits Grok to the tools you name; the xai-sdk spells it allowed_tool_names, and headers as extra_headers. X-ELDRICK-Platform: grok files your usage under Grok. Each analyze_fitting uses one of your fittings; every other tool is free.

Cursor desktop

1. Add ELDRICK to Cursor, or add it to ~/.cursor/mcp.json:

2. {
     "mcpServers": {
       "eldrick": { "url": "https://api.eldrick.com/mcp" }
     }
   }

3. Open Settings → MCP and sign in to eldrick.

VS Code GitHub Copilot agent mode

1. Add ELDRICK to VS Code, or add it to .vscode/mcp.json:

2. {
     "servers": {
       "eldrick": { "type": "http", "url": "https://api.eldrick.com/mcp" }
     }
   }

3. Start the server from the file’s CodeLens and sign in when VS Code asks.

Windsurf desktop

1. Add ELDRICK to mcp_config.json (Cascade → MCP servers → View raw config):

   {
     "mcpServers": {
       "eldrick": { "serverUrl": "https://api.eldrick.com/mcp" }
     }
   }

2. Refresh the MCP list and sign in.

Any other MCP client

1. Add a remote MCP server (Streamable HTTP) with the URL https://api.eldrick.com/mcp.
2. Sign in when the client asks. ELDRICK supports OAuth 2.1 with PKCE, client metadata documents and dynamic registration, so most clients need nothing else.
3. No OAuth in your client? Send an API key from the dashboard as Authorization: Bearer eld_.... Never paste a key into a chat.