# Fairquery Agent Trust & Data Safety

> Fairquery Agent Trust & Data Safety is a freemium MCP server for security. Redact PII and secrets, check emails, screen sanctions and look up OSV vulnerabilities. It runs locally on your machine and is started by your AI client.

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

## About

Thirteen tools cover four checks an agent runs into when it handles untrusted input: is there personal data or a secret in this text, is this email address real, is this person or company on a sanctions list, and is this package version vulnerable. Eight tools are free and run on your machine; the two OSV lookups call api.osv.dev directly.

The five deeper tools run public Fairquery Apify Actors with your own APIFY_TOKEN and are billed to your Apify account, for example $0.79 per 1,000 email deliverability checks or $3.00 per 1,000 names screened (plus a small per-call start fee). Without a token a paid tool returns a named APIFY_TOKEN_MISSING error and spends nothing.

Redaction can use placeholder, mask or hash styles and can return a map so pii_restore_text puts the original values back into a model's answer. Outputs are paged and every tool description follows a WHAT, WHEN, WHEN NOT, COST, RETURNS, EXAMPLE layout. It runs on Node.js 20 or later over stdio, or with --http for Streamable HTTP.

## Features

- **Local PII redaction:** Find and redact PII and secrets with placeholder, mask or hash styles, then restore them later.
- **Email checks:** Free syntax and typo checks, plus paid DNS, MX, SPF and DMARC verification.
- **Sanctions screening:** Fuzzy name screening against OFAC, EU, UK and UN lists.
- **OSV lookups:** Query exact package versions and fetch full advisories.
- **Lead triage:** trust_screen_lead merges email and sanctions checks into pass, review or block.

## Good for

- Strip personal data from a support ticket before summarising it
- Screen new suppliers against sanctions lists
- Check signup emails for typos and disposable domains
- Audit a lockfile for known vulnerabilities before approving dependencies

## Install

### Claude Code (Terminal)

```sh
claude mcp add fairquery-agent-trust-mcp --env APIFY_TOKEN='<APIFY_TOKEN>' -- npx -y @fairquery/agent-trust-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "fairquery-agent-trust-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fairquery/agent-trust-mcp"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "fairquery-agent-trust-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fairquery/agent-trust-mcp"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
```

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

```json
{
  "servers": {
    "fairquery-agent-trust-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@fairquery/agent-trust-mcp"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "fairquery-agent-trust-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fairquery/agent-trust-mcp"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "fairquery-agent-trust-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fairquery/agent-trust-mcp"
      ],
      "env": {
        "APIFY_TOKEN": "<APIFY_TOKEN>"
      }
    }
  }
}
```

## Tools

- `pii_list_detectors`: Catalog of detectors, redaction styles and pricing for the paid tools.
- `pii_scan_text`: Finds PII and secrets in text and shows masked values only.
- `pii_redact_text`: Redacts with placeholder, mask or hash style and can return a placeholder map.
- `pii_restore_text`: Puts original values back into placeholder text using the map.
- `pii_guard_documents`: Paid: adds NER names and addresses, URLs, PDFs and restore mode.
- `email_check_syntax`: Free syntax, normalization, typo, disposable, role and free-provider checks.
- `email_validate_deliverability`: Paid: DNS and MX, null MX, SPF, DMARC, provider and verdict.
- `sanctions_list_sources`: Lists covered sanctions sources and issuing authorities.
- `sanctions_screen_names`: Paid: fuzzy screening against OFAC, EU, UK and UN lists.
- `osv_query_packages`: Free: checks up to 200 exact package versions for vulnerabilities.
- `osv_get_vulnerability`: Returns full OSV advisory records.
- `osv_audit_dependencies`: Paid: audits a manifest or lockfile with severity and fixes.
- `trust_screen_lead`: Paid: runs email and sanctions checks in parallel and returns pass, review or block.

## FAQ

### Which tools are free?

Eight of the thirteen run locally with no account; the two OSV lookups call the free OSV.dev API.

### How are the paid tools billed?

Through your own Apify account using your APIFY_TOKEN, at the per-result prices listed.

### Does the free part send data to Fairquery?

The page says the free tools never contact Apify or Fairquery, and the PII tools make no network calls.

### What Node.js version is needed?

Node.js 20 or later.

### 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 fairquery-agent-trust-mcp --env APIFY_TOKEN='<APIFY_TOKEN>' -- npx -y @fairquery/agent-trust-mcp

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

The closest alternatives to Fairquery Agent Trust & Data Safety are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/fairquery-agent-trust-and-data-safety-2
