DataCharter MCP Server

Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.

Local serverstdioPython

What is the DataCharter MCP server?

DataCharter MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.

What you get

Beyond local federation and governed agent access, you also get:

  • Your contracts are the catalog. — charter.yaml describes sources, tables,
  • Real federation, not just a shared connection. — Filters and projections are
  • Local-first. — One process, your machine, no cloud dependency. The optional
  • The workspace is a directory. — charter.yaml + queries/*.sql +

What the assistant can call

Once DataCharter is connected, these are the calls the assistant has available:

  • Clean — room math, one YAML line.** Policies like aggregates only and groups of at least 10 are enforced by query
  • Local — first.** One process, your machine, no cloud dependency. The optional

Configuration and credentials

You will need 2 environment variables: OPENAI_BASE_URL, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

datacharter on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. DataCharter's toolset — Clean, Local — is a fair guide to whether it matches your workflow. It is maintained by datacharter; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the datacharter mcp server does with a few real requests.

Available tools

ToolWhat it does
Cleanroom math, one YAML line.** [Policies](https://datacharter.dev/policies.html) like aggregates only and groups of at least 10 are enforced by query analysis — k-anonymity suppression and join limits, written in plain Engl
Localfirst.** One process, your machine, no cloud dependency. The optional

How to install the DataCharter MCP server

{
  "mcpServers": {
    "datacharter": {
      "command": "uvx",
      "args": ["datacharter"],
      "env": {
        "OPENAI_BASE_URL": "your-value",
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OPENAI_BASE_URLEndpoint or connection string the server talks to.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use DataCharter to Clean.
  • Use DataCharter to Local.

Frequently asked questions

It connects DataCharter to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Clean, Local) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with DataCharter directly.