Connect your Agent
Connect Claude, ChatGPT, Gemini, and other MCP-compatible chat clients to your semantic models
Everything you can do analyzing data in the Credible App, you can do in the agent you prefer — Claude, ChatGPT, Gemini, or any MCP-compatible chat client. Connect it to Credible and it answers questions grounded in your governed semantic models — no hallucinated field names, no misread schemas — powered by the same AI Analytics Engine and the same open-source agent skills behind workspace chat. Same analysis discipline, your agent.
Personal agents connect to Credible's MCP server and authenticate with OAuth: add the server, complete the sign-in flow as yourself, and start asking questions. Because you sign in as yourself, every query is governed as you — your model's access rules apply exactly as they do in the app.
Use your organization's MCP server URL: https://<your-org>.mcp.credibledata.com/mcp
To restrict analysis to a specific workspace, use the workspace-scoped URL instead — you can copy it from your workspace settings page. See MCP Tools for details on scoping.
Using an IDE or CLI coding agent — VS Code Copilot, Claude Code, Gemini CLI, or Windsurf? See Connect your Coding Agent for connecting it to your published models.
- Click on user icon (bottom-left)
- Connectors
- Browse
- Click on the link "add a custom one" (note this is not a button)
- Enter Name and URL:
https://<your-org>.mcp.credibledata.com/mcp - Leave advanced settings alone
- Click "connect" on the next page
If you don't see the option to add custom connectors on an enterprise account, contact your Claude administrator to enable this feature.
- Click on user icon (bottom-left)
- Settings
- Apps & Connectors
- Click "Create"
- Add a name (e.g., "Credible") and the server URL:
https://<your-org>.mcp.credibledata.com/mcp - Leave authentication as "OAuth" and click "Create"
- Follow the OAuth authentication flow
- Now you can ask ChatGPT to use the Credible tool (or whatever you named it)
You may need to enable "Dev mode" in Apps & Connectors settings (scroll to bottom) before you can create custom connectors.
Cowork uses the same connectors as your Claude account — a connector added once works across claude.ai, Claude Desktop, and Cowork.
- In Cowork, open the connector settings and click the + icon
- Select Add a Custom Connector
- Give the connector a name (e.g., "Credible") and enter the server URL:
https://<your-org>.mcp.credibledata.com/mcp - Click Add, then complete the OAuth authentication flow
- Enable the connector in your conversation to start asking questions
On Team and Enterprise plans, an Organization Owner must first add the connector under Organization settings → Connectors; members can then connect it from Customize → Connectors.
The consumer Gemini web app does not support custom MCP connectors. Use Gemini Enterprise, or connect the Gemini CLI instead.
In Gemini Enterprise, connect Credible as a custom MCP server data store:
- In the Gemini Enterprise console, go to Data Stores → Create Data Store and select Custom MCP Server
- Enter the MCP Server URL:
https://<your-org>.mcp.credibledata.com/mcp, along with the OAuth configuration for your organization - Attach the data store to your Gemini Enterprise app under Connected data sources
- In the Gemini chat input, open the connector menu, Authorize the Credible connector, and toggle it on
Gemini Enterprise requires OAuth client credentials to authorize the connection — contact support and we'll help you get set up.
What Your Agent Can Do
Once connected, your agent has the same two tools every Credible surface uses — get_context to discover governed entities in your models, and execute_query to run Malloy queries against them — and Credible's open-source skills encode the discipline to use them well: parsing your question into the right search phrases, finding the right sources and views, writing correct Malloy, choosing sensible visualizations, and sanity-checking results before trusting them. In your agent, that means you can:
- Ask data questions in plain language — "What were our top products by revenue last quarter?" — and get answers grounded in your governed definitions, not guesses
- Iterate in conversation — follow up, refine, and drill into drivers, with each query building on the matched entities from the last
- Analyze alongside your other context — combine Credible answers with the documents, tools, and conversation already in your agent
- Stay governed throughout — every query runs through Credible, ACL'd and audit-logged as you
See the MCP Tools reference for tool parameters and details.