Enterprise DNAEnterprise DNA
MMCP ServersDeveloperlow

datacharter/datacharter

by Various

Your data, explored locally — and your AI agents kept on a leash. A federated data explorer with governed agentic access.

Visit siteSubmit your build →

MCP

datacharter/datacharter

Added 3 Sept 2026

#data-catalog#data-contracts#data-engineering#data-exploration#data-governance#duckdb#local-first#mcp
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

A federated data explorer that runs locally and provides governed agentic access for AI agents. Built in Python, it lets you explore data across sources while keeping agent actions constrained.

Best for

Best for
Python developers who want local, governed data access for AI agents.

Use cases

  • Explore data locally across federated sources
  • Give AI agents governed, constrained access to datasets
  • Keep sensitive data on-premises while enabling agent queries

How to use

Install

uvx datacharter serve          # needs

Clients listed in this record (not verified here)

Claude Code, Cursor, Cline, ChatGPT

Notes

12 stars on GitHub. Last updated 2026-09-02. Licensed Apache-2.0.

Pros

  • Local execution keeps data on your own machine
  • Federated design supports multiple data sources
  • Governed access helps control what agents can do

Cons

  • Very few stars, indicating limited adoption
  • Python-only implementation may not fit all stacks
  • Governance features are not described in detail
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to MCP ServersSubmit your own entry →