> For the complete documentation index, see [llms.txt](https://www.conserver.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.conserver.io/mcp-server.md).

# MCP Server

Where to start with the vCon MCP Server, the open-source Model Context Protocol server that lets AI assistants query and update a store of vCons.

The vCon MCP Server gives an AI assistant or agent access to a store of vCons over the [Model Context Protocol](https://modelcontextprotocol.io). It runs over stdio or Streamable HTTP, exposes 46 tools in seven groups plus resources and prompts, and stores vCons in Supabase Postgres with optional Redis caching and pgvector semantic search.

The code is at [vcon-dev/vcon-mcp](https://github.com/vcon-dev/vcon-mcp), MIT-licensed TypeScript, published as the npm package `vcon-mcp` and the Docker image `public.ecr.aws/r4g1k2s3/vcon-dev/vcon-mcp`. These pages describe release 1.10.0.

## Pages in this section

* [What is the vCon MCP Server?](https://www.conserver.io/mcp-server/what-is-the-vcon-mcp-server.md): what it does, how MCP works, when to use it, how it relates to the conserver.
* [Tool Reference](https://www.conserver.io/mcp-server/tool-reference.md): every tool with its key parameters, plus resources and prompts.
* [Contract Tools](https://www.conserver.io/mcp-server/contract-tools.md): the envelope, paging, byte budgets and error codes of the LLM-facing tools.
* [Transport and Deployment](https://www.conserver.io/mcp-server/transport-and-deployment.md): transports, keys, tool profiles, tenancy, environment variables, Docker and npm.
* [How the vCon MCP Server is Built](https://www.conserver.io/mcp-server/how-the-vcon-mcp-server-is-built.md): validation, plugins, the write and read paths, tables and search.
* [Field-Name Migration](https://www.conserver.io/mcp-server/field-name-migration.md): how `critical` and `amended` replace `must_support` and `appended`.

## Elsewhere

* [Source on GitHub](https://github.com/vcon-dev/vcon-mcp)
* [mcp.conserver.io](https://mcp.conserver.io/), the generated technical reference


---

# 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://www.conserver.io/mcp-server.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.
