> For the complete documentation index, see [llms.txt](https://docs.podigee.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.podigee.com/documentation/start-here/ai-agents/connect-and-authorize/connect-another-compatible-mcp-client.md).

# Connect another compatible MCP client

Connect a compatible remote MCP client to Podigee through the protected public endpoint.

Connect an AI application that supports remote Model Context Protocol (MCP) servers and OAuth.

## Before you start

* Confirm that the client supports remote Streamable HTTP MCP servers.
* Confirm that the client supports OAuth authorization for protected MCP resources.
* Have a Podigee account on a current plan. Connecting AI assistants is part of each current plan, starting with Launch.
* Use the production Podigee MCP endpoint only for production account data.

## Add the Podigee server

1. Open the client's MCP server or connection settings.
2. Add a remote HTTP server.
3. Enter this endpoint:

   ```
   https://mcp.podigee.com/mcp
   ```
4. Start the connection.
5. Allow the client to open the Podigee authorization page.
6. Sign in to Podigee.
7. Review the client name, selected account, return host, and requested permissions.
8. Approve the connection only when all details are correct.

Do not enter the authorization-server URL as the MCP endpoint. A compatible client discovers the authorization server from the protected-resource metadata.

Podigee does not keep a list of permitted clients. A client that Podigee does not know by name shows on the authorization page with the name it gives itself, and with the host or the computer that the sign-in returns to. Approve the connection only when you started it.

## Connect Cursor

1. In Podigee, go to **Data & integrations > Connected apps**.
2. Under **Cursor**, select **Add to Cursor**.
3. In Cursor, confirm the new MCP server.
4. Start the sign-in when Cursor asks, and complete the Podigee authorization in your browser.

## Connect VS Code

1. In Podigee, go to **Data & integrations > Connected apps**.
2. Under **VS Code**, select **Add to VS Code**.
3. In VS Code, confirm the new MCP server.
4. Start the server, and complete the Podigee authorization in your browser.

## Connect Gemini CLI

1. Run this command:

   ```sh
   gemini mcp add --transport http podigee https://mcp.podigee.com/mcp
   ```
2. Start Gemini CLI and enter `/mcp auth podigee`.
3. Complete the Podigee authorization in your browser.

## Verify the connection

Ask the client to identify the connected account and list accessible podcasts without making a change. A client can call `get_me` and `list_podcasts` for this check.

## Expected result

The client completes OAuth, connects to `https://mcp.podigee.com/mcp`, and returns the selected Podigee tenant and accessible podcasts.

## If the client cannot connect

Check that the client supports Streamable HTTP, protected-resource metadata, authorization-code OAuth with S256 Proof Key for Code Exchange (PKCE), and bearer authentication.

Do not work around an OAuth failure by pasting a token into a chat message. Use a protected client secret field or the personal-access-token path when the client supports one.

## Next step

[Choose permissions and scopes](/documentation/start-here/ai-agents/connect-and-authorize/choose-permissions-and-scopes.md) before you enable write work.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.podigee.com/documentation/start-here/ai-agents/connect-and-authorize/connect-another-compatible-mcp-client.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.