How does DataCharter protect sensitive data from AI agents?

It automatically detects PII and denies agent access by default, applies per-column masking, and enforces policies like aggregation and k-anonymity to govern data exposure.

Can I control what data each AI agent can access?

Yes, access can be granted or denied at the source, table, and column level via UI or data contracts, allowing fine-grained control over agent-visible data.

Does DataCharter allow write operations on data sources?

No, the query engine is read-only by design to prevent any data modification or filesystem changes.

How can I audit AI agent data access?

DataCharter logs every agent query with tamper-evident, hash-chained audit records and supports verification commands and alarm tripwires for policy violations.

Datacharter

databasesdata-governancepii-maskingfederationai-agent-access

Local federated data query engine with read-only guards, PII masking, and per-column AI agent access control.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

We couldn’t automatically confirm this listing starts correctly

We ran the install command below but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx datacharter

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 4d ago.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Configure Environment Variables (API Keys, Tokens, Options):

Add required secrets below — values are included directly in the generated snippet so you can copy and paste with confidence.

Quick Add:

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "datacharter-datacharter": {
      "command": "uvx",
      "args": [
        "datacharter"
      ],
      "env": {
        "DATA_CHARTER_CONFIG": "YOUR_VALUE_HERE",
        "DATA_CHARTER_LOG_LEVEL": "YOUR_VALUE_HERE"
      }
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

DataCharter enables local querying across diverse data sources including files (CSV, Parquet, Excel) and databases (Postgres, Snowflake, BigQuery, DuckDB, and more) in a federated manner. It enforces strict, contract-based governance on AI agent data access with read-only protections, automatic PII detection and masking, and fine-grained per-column permissions. Use it to securely expose governed data subsets to AI agents while maintaining auditability, policy enforcement, and reproducibility.

Use cases

Query and join data across multiple local files and remote databases in one SQL statement

Control and audit AI agent access to sensitive data with per-column masking and policies

Define and enforce data governance contracts including PII masking and k-anonymity

Evaluate and improve agent accuracy with guided data usage and local evaluation tools

Automate data quality checks and schema drift detection in CI workflows

Key features

Federated querying across files and databases locally

Read-only query engine with no write or filesystem side effects

Automatic PII detection and default agent access denial

Per-source, per-table, and per-column access controls for AI agents

Tamper-evident audit logging of agent queries and access

Policy enforcement for aggregation, group sizes, and data masking

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by Datacharter.

Extracted Tool Capabilities

Federated querying across files and databases locally

Read-only query engine with no write or filesystem side effects

Automatic PII detection and default agent access denial

Per-source, per-table, and per-column access controls for AI agents

Tamper-evident audit logging of agent queries and access

Policy enforcement for aggregation, group sizes, and data masking

Documentation Overview

DataCharter

Query all your data locally. Hand agents exactly the columns you choose.

A local SQL workspace over files and databases, federated by DuckDB and governed by charter.yaml. Agents get read-only, PII-masked access to what the contract grants. Apache-2.0. No paid edition.

datacharter.dev · Docs · Desktop · GovBench · Deploy

Two ways in. Same kernel.

Laptop

Drop a file. Query it. Chart it. An agent sees ••• where PII lives.

uvx datacharter serve          # demo workspace, http://127.0.0.1:8321
# or: datacharter init --from && datacharter serve
# or: datacharter init --template life && datacharter serve --local

No terminal: desktop app (beta). macOS (Apple Silicon) or Windows. Unsigned until Apple secrets exist.

brew install datacharter/tap/datacharter   # macOS
pip install datacharter                    # Python 3.11+

The workspace is a directory: charter.yaml, queries/, guides/. Commit it. Secrets stay out. Optional agent: SpaceXAI, Claude Code, Ollama (--local), or any OpenAI-compatible endpoint.

Company

The same binary, on a shared MCP endpoint. Identities live in git, not on our servers. No rows leave your infrastructure.

datacharter mcp --http --host 0.0.0.0   # OAuth env required off loopback
helm install datacharter ./chart \
  --set oauth.issuer=... --set oauth.audience=... --set oauth.jwksUri=...
datacharter govbench --json             # cite corpus govbench-v1

MCP Streamable HTTP (POST /mcp) with optional OAuth 2.1
principals: and grants: in charter.yaml (default-deny on HTTP)
Helm chart and OCI image
Hash-chained audit plus SIEM JSON/OTLP
GovBench: frozen 28-attack corpus, grade A-F

Wrap someone else's MCP server: datacharter mcp --guard "npx -y some-mcp-server".

What the contract enforces

PII default-deny, row filters, plain-English policies (aggregates only), canaries, a flight recorder, datacharter redteam, access diff on PRs. CLI reference: docs/cli.md. Security: docs/security.md.

Status: pre-release. V1 in development.

Privacy

Runs on your machine or in your cluster. No telemetry. No DataCharter-operated data plane. Privacy Policy.

License

Apache-2.0

Read the full README →View source on GitHub →

Related MCP Servers

View all in Databases View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5d ago

Most recent push to the default branch.

Install check

Inconclusive

Didn't respond in our test window — often a slow first install.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Datacharter

It supports local CSV, Parquet, JSON, Excel files and databases including Postgres, MySQL, SQLite, SQL Server, Snowflake, BigQuery, DuckDB, Iceberg, and Delta.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/datacharter-datacharter?style=directory)](https://allmcps.com/mcp/datacharter-datacharter)

HTML Embed

<a href="https://allmcps.com/mcp/datacharter-datacharter"><img src="https://allmcps.com/api/badge/datacharter-datacharter?style=directory" alt="Datacharter on AllMCPs" /></a>

Technical Specs & Signals

CategoryDatabases

PricingFree

12/12 checks healthy over the last 42d

53Quality signal: Good · 53/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools24/30

Adoption & activity6/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · datacharter (PyPI)

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🗄️ Databases →Best MCP servers for Databases →Alternatives to Datacharter →Install in Claude Desktop Install in Cursor Install in VS Code

Datacharter

databasesdata-governancepii-maskingfederationai-agent-access

Local federated data query engine with read-only guards, PII masking, and per-column AI agent access control.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

We couldn’t automatically confirm this listing starts correctly

We ran the install command below but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx datacharter

No response to initialize.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Configure Environment Variables (API Keys, Tokens, Options):

Add required secrets below — values are included directly in the generated snippet so you can copy and paste with confidence.

Quick Add:

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "datacharter-datacharter": {
      "command": "uvx",
      "args": [
        "datacharter"
      ],
      "env": {
        "DATA_CHARTER_CONFIG": "YOUR_VALUE_HERE",
        "DATA_CHARTER_LOG_LEVEL": "YOUR_VALUE_HERE"
      }
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

Use cases

Query and join data across multiple local files and remote databases in one SQL statement

Control and audit AI agent access to sensitive data with per-column masking and policies

Define and enforce data governance contracts including PII masking and k-anonymity

Evaluate and improve agent accuracy with guided data usage and local evaluation tools

Automate data quality checks and schema drift detection in CI workflows

Key features

Federated querying across files and databases locally

Read-only query engine with no write or filesystem side effects

Automatic PII detection and default agent access denial

Per-source, per-table, and per-column access controls for AI agents

Tamper-evident audit logging of agent queries and access

Policy enforcement for aggregation, group sizes, and data masking

Capabilities & Tool Schemas

Inspect callable tools, capabilities, and parameters exposed to AI agents by Datacharter.

Extracted Tool Capabilities

Federated querying across files and databases locally

Read-only query engine with no write or filesystem side effects

Automatic PII detection and default agent access denial

Per-source, per-table, and per-column access controls for AI agents

Tamper-evident audit logging of agent queries and access

Policy enforcement for aggregation, group sizes, and data masking

Documentation Overview

DataCharter

Query all your data locally. Hand agents exactly the columns you choose.

A local SQL workspace over files and databases, federated by DuckDB and governed by charter.yaml. Agents get read-only, PII-masked access to what the contract grants. Apache-2.0. No paid edition.

datacharter.dev · Docs · Desktop · GovBench · Deploy

Two ways in. Same kernel.

Laptop

Drop a file. Query it. Chart it. An agent sees ••• where PII lives.

uvx datacharter serve          # demo workspace, http://127.0.0.1:8321
# or: datacharter init --from && datacharter serve
# or: datacharter init --template life && datacharter serve --local

No terminal: desktop app (beta). macOS (Apple Silicon) or Windows. Unsigned until Apple secrets exist.

brew install datacharter/tap/datacharter   # macOS
pip install datacharter                    # Python 3.11+

The workspace is a directory: charter.yaml, queries/, guides/. Commit it. Secrets stay out. Optional agent: SpaceXAI, Claude Code, Ollama (--local), or any OpenAI-compatible endpoint.

Company

The same binary, on a shared MCP endpoint. Identities live in git, not on our servers. No rows leave your infrastructure.

datacharter mcp --http --host 0.0.0.0   # OAuth env required off loopback
helm install datacharter ./chart \
  --set oauth.issuer=... --set oauth.audience=... --set oauth.jwksUri=...
datacharter govbench --json             # cite corpus govbench-v1

MCP Streamable HTTP (POST /mcp) with optional OAuth 2.1
principals: and grants: in charter.yaml (default-deny on HTTP)
Helm chart and OCI image
Hash-chained audit plus SIEM JSON/OTLP
GovBench: frozen 28-attack corpus, grade A-F

Wrap someone else's MCP server: datacharter mcp --guard "npx -y some-mcp-server".

What the contract enforces

Status: pre-release. V1 in development.

Privacy

Runs on your machine or in your cluster. No telemetry. No DataCharter-operated data plane. Privacy Policy.

License

Apache-2.0

Read the full README →View source on GitHub →

Related MCP Servers

View all in Databases View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5d ago

Most recent push to the default branch.

Install check

Inconclusive

Didn't respond in our test window — often a slow first install.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Datacharter

It supports local CSV, Parquet, JSON, Excel files and databases including Postgres, MySQL, SQLite, SQL Server, Snowflake, BigQuery, DuckDB, Iceberg, and Delta.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/datacharter-datacharter?style=directory)](https://allmcps.com/mcp/datacharter-datacharter)

HTML Embed

<a href="https://allmcps.com/mcp/datacharter-datacharter"><img src="https://allmcps.com/api/badge/datacharter-datacharter?style=directory" alt="Datacharter on AllMCPs" /></a>

Technical Specs & Signals

CategoryDatabases

PricingFree

12/12 checks healthy over the last 42d

53Quality signal: Good · 53/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools24/30

Adoption & activity6/15

Community engagement0/10

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · datacharter (PyPI)

★ Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🗄️ Databases →Best MCP servers for Databases →Alternatives to Datacharter →Install in Claude Desktop Install in Cursor Install in VS Code