# Fairquery Agent Trust & Data Safety

> Fairquery Agent Trust & Data Safety is a freemium MCP server for security. Free local PII redaction, email checks and OSV lookups, plus paid sanctions screening. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, API
- **Website:** https://getfairquery.com/posts/give-ai-agent-trust-safety-tools-mcp-server/
- **MCP Registry name:** com.getfairquery/agent-trust-mcp
- **Categories:** security
- **Listing updated:** 2026-11-15

## About

Fairquery's server bundles four checks an agent often needs before acting on untrusted input: finding or redacting personal data and secrets, vetting email addresses, screening names against sanctions lists, and checking package versions against OSV.dev. Eight of the 13 tools are free and run on your machine; the PII tools make no network calls at all and the OSV lookups contact only api.osv.dev.

The five deeper tools run Fairquery's public Apify Actors with your own APIFY_TOKEN and are billed to your Apify account per result. Without a token, a paid tool returns a named APIFY_TOKEN_MISSING error and spends nothing. Sanctions screening covers OFAC, EU, UK and UN lists.

PII redaction can swap values for placeholders and later restore them in an LLM answer using the returned map. Tool outputs are paged and errors use named codes. Node.js 20 or later is required for the npm package; a hosted streamable-HTTP endpoint also exists.

## Features

- **Local PII and secret redaction:** Placeholder, mask or hash styles, with a map to restore originals.
- **Email syntax checks:** Flags typos, disposable domains and role addresses without DNS lookups.
- **Sanctions screening:** Fuzzy name matching against OFAC, EU, UK and UN lists (paid).
- **OSV vulnerability lookups:** Checks up to 200 exact package versions against OSV.dev.
- **Lead screening:** Combines email and sanctions checks into a pass, review or block decision (paid).
- **Named errors and paging:** Results page with limit and offset, and errors carry stable codes.

## Good for

- Redact a support ticket before sending it to a model
- Catch throwaway or mistyped signup emails
- Pre-screen suppliers against sanctions lists
- Check a dependency version for known vulnerabilities before installing
- Audit a lockfile for vulnerable packages in CI

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agent-trust-mcp https://mcp.getfairquery.com/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.getfairquery.com/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-trust-mcp": {
      "url": "https://mcp.getfairquery.com/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agent-trust-mcp": {
      "type": "http",
      "url": "https://mcp.getfairquery.com/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-trust-mcp": {
      "serverUrl": "https://mcp.getfairquery.com/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agent-trust-mcp": {
      "type": "http",
      "url": "https://mcp.getfairquery.com/mcp"
    }
  }
}
```

## Tools

- `pii_list_detectors`: Lists detectors, redaction styles and pricing for the paid tools.
- `pii_scan_text`: Finds PII and secrets in text, showing masked values only.
- `pii_redact_text`: Redacts text with placeholder, mask or hash style.
- `pii_restore_text`: Restores original values into placeholder text using a map.
- `pii_guard_documents`: Paid document guard adding NER, URLs and PDFs.
- `email_check_syntax`: Checks email syntax, typos, disposable and role addresses.
- `email_validate_deliverability`: Paid check of DNS, MX, SPF and DMARC.
- `sanctions_list_sources`: Lists covered sanctions sources and issuing authorities.
- `sanctions_screen_names`: Paid fuzzy screening of names against sanctions lists.
- `osv_query_packages`: Reports whether exact package versions are vulnerable.
- `osv_get_vulnerability`: Returns a full OSV advisory record.
- `osv_audit_dependencies`: Paid audit of a manifest or lockfile with fixes.
- `trust_screen_lead`: Paid email check and sanctions screening merged into one decision.

## FAQ

### Which tools are free?

Eight tools need no account and run locally, except the OSV lookups, which call api.osv.dev.

### How are paid tools billed?

Through your own Apify account. Examples include $0.79 per 1,000 emails for deliverability checks and $3.00 per 1,000 names for sanctions screening, plus a small start fee per call batch.

### Do I need a token to try it?

No. Leave out APIFY_TOKEN to use only the free tools.

### How does it install?

Run npx -y @fairquery/agent-trust-mcp with Node.js 20 or later, or use the hosted streamable-HTTP endpoint.

### Is Fairquery Agent Trust & Data Safety free?

Fairquery Agent Trust & Data Safety has a free plan, with paid plans for more usage or features.

### How do I add Fairquery Agent Trust & Data Safety to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-trust-mcp https://mcp.getfairquery.com/mcp

### What are the best alternatives to Fairquery Agent Trust & Data Safety?

The closest alternatives to Fairquery Agent Trust & Data Safety are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [SynomosAI Governance MCP](https://ai-powered.com/mcp/synomosai-governance-mcp-2): SynomosAI Governance MCP is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/fairquery-agent-trust-and-data-safety
