> For the complete documentation index, see [llms.txt](https://coldbox.ortusbooks.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://coldbox.ortusbooks.com/getting-started/agentic-development/cbmcp.md).

# cbMCP — Live App Introspection

cbMCP — expose your running ColdBox application as an MCP server so AI agents can introspect it live.

**cbMCP** turns your running ColdBox application into a fully-compliant MCP server. Any MCP-capable AI client (Claude, Copilot, Cursor) can connect and get live answers about your app — no terminal, no log-diving, no code grepping.

🚀 **BoxLang only.**

```bash
box install cbMCP
```

## What Agents Can Ask

Once connected, your AI assistant can answer questions like:

* "What routes does my app expose under `/api`?"
* "Show me all WireBox singletons."
* "Are there any ERROR log entries in the last hour?"
* "Run the nightly-cleanup scheduler task now."

cbMCP ships with **10 tool classes (50+ tools)** covering routing, handlers, WireBox, CacheBox, LogBox, schedulers, and more — plus MCP Resources (ambient context auto-injected into conversations) and MCP Prompts (ready-made workflows).

## Setup

```bash
box install cbMCP
```

No extra configuration is required. Once the module is installed and your application boots, the MCP endpoint is live at `http://<host>:<port>/cbmcp`.

Connect your MCP-compatible client to it — for stdio-based clients like Claude Desktop, use the HTTP bridge:

```json
{
    "mcpServers" : {
        "coldbox" : {
            "command" : "npx",
            "args"    : [ "-y", "@depasquale/mcp-http-stdio-bridge", "--url", "http://127.0.0.1:60299/cbmcp" ]
        }
    }
}
```

VS Code and Cursor can connect to the HTTP endpoint directly in their MCP settings.

## Go Deeper

Full tool reference, resources, prompts, and security configuration: [ColdBox MCP Server](/ai/coldbox-mcp-server.md).

## See Also

* [AI Runtime Capabilities](/ai/ai.md)
* [ColdBox CLI AI Setup](/getting-started/agentic-development/coldbox-cli-ai-setup.md)


---

# 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://coldbox.ortusbooks.com/getting-started/agentic-development/cbmcp.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.