# MCP

## Bitte MCP Proxy

**Convert any agent deployed on** [**Bitte**](https://bitte.ai) **into a fully-compliant** [**Model Context Protocol (MCP)**](https://github.com/vercel/mcp) **server.**

The **Bitte MCP Proxy** makes every agent on the Bitte platform accessible through standardized MCP endpoints. No configuration, no redeployments—just plug-and-play interoperability.

***

### 🚀 Features

* **Agent-to-MCP Conversion**\
  Every agent deployed on Bitte is instantly exposed as an MCP server via HTTP.
* **Seamless Integration**\
  No changes to your agent code. MCP clients can connect directly via a consistent interface.
* **Standard MCP Interface**\
  Agents expose standardized MCP fields:
  * `tools`
  * `resources`
  * `prompt`
  * `input_schema`, `output_schema`
  * and more...

***

### 🔗 Endpoint Format

```http
GET https://mcp.bitte.ai/mcp?agentId={YOUR_AGENT_ID}
```

Replace `{YOUR_AGENT_ID}` with the actual ID of the agent you deployed on Bitte.

If you want to find an agent ID go to <https://bitte.ai/agents> and then open the agent you want.

<figure><img src="https://74933262-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FB52AZELB8jl58pzYsH6O%2Fuploads%2FJC5MR4iW6fMSxsMmzkSU%2FCaptura%20de%20ecra%CC%83%202025-07-03%2C%20a%CC%80s%2017.09.03.png?alt=media&#x26;token=d48e458b-2d4b-4194-8022-2413d5164de6" alt=""><figcaption><p>MCP link in the agent page</p></figcaption></figure>

***

### 🛠 Example

If your agent is deployed with ID `rhea-ai-eight.vercel.app`, you can call it directly:

```
https://mcp.bitte.ai/mcp?agentId=rhea-ai-eight.vercel.app
```

This returns the MCP server metadata and allows tool usage via standard MCP request formats.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.bitte.ai/agents/mcp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.