mcpField
T
trustlists

trustlists

Local
trustlists.orgSecurity0Updated 4w ago

About trustlists

trustlists is an MCP server for searching public vendor trust centers and handling related security workflows. It also supports signed-in SOC 2 report analysis and requests for access to vendor trust centers.

Key features

  1. 01Search, look up, and filter trust centers
  2. 02Map project manifests to vendor records
  3. 03Analyze local SOC 2 PDFs
  4. 04Request vendor trust-center access

Use cases

  1. 01Find a vendor’s public security documentation
  2. 02Check vendors referenced by project dependencies
  3. 03Review a SOC 2 report
  4. 04Request access to a private trust center

MCP support

Exposes directory search, lookup, browsing, and dependency-audit tools to MCP clients, plus account-based SOC 2 analysis and vendor access requests. Clients can run the package locally or use the hosted endpoint after OAuth sign-in.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"trustlists": {
"command": "npx",
"args": [
"-y",
"@trustlists/mcp"
]
}
}
}
Run commandnpx -y @trustlists/mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@trustlists/mcp0.3.0

Tools

15

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitintegerNoMax results to return (1-20, default 8).
querystringYesCompany name or domain to search for (min 2 characters).

Details

From the project README

@trustlists/mcp

MCP server that gives AI assistants access to the public trustlists directory, plus signed-in SOC 2 analysis and trust-center access requests.

This npm package powers the trustlists_ plugin for Cursor, Claude Code, and other Model Context Protocol clients.

Installation

You don't install this package directly. It is spawned by your MCP-aware AI client.

Cursor

The trustlists_ plugin handles installation. Or add it manually to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "trustlists": {
      "command": "npx",
      "args": ["-y", "@trustlists/mcp"]
    }
  }
}
Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "trustlists": {
      "command": "npx",
      "args": ["-y", "@trustlists/mcp"]
    }
  }
}

Tools

Free (no account)
ToolDescription
trustlists_searchSearch thousands of trust centers by name or domain
trustlists_lookupLook up a single vendor by exact domain
trustlists_browseFilter by platform, listed framework, or CSA STAR level
trustlists_audit_dependenciesMap project manifests to public vendor trust centers
Account

Sign in with trustlists_login (device code). Credentials are stored in ~/.trustlists/auth.json on this machine. The hosted endpoint at mcp.trustlists.org/mcp serves these tools after an OAuth sign-in instead, with SOC 2 uploads in the trustlists app (trustlists_soc2_upload) in place of local PDF paths.

ToolDescription
trustlists_login / logout / whoamiDevice-code sign-in and session
trustlists_soc2_analyze / status / reportAnalyze local SOC 2 PDFs (preview, then confirmCredits)
trustlists_requester_profileIdentity used on vendor access forms
trustlists_access_request / status / continueRequest SafeBase/Vanta access (preview, then confirm)
trustlists_access_request_batchSame, up to 5 vendors, one confirm

Directory labels show what a public record lists. They do not independently prove certification scope, validity, legal compliance, or security quality.

Supported manifest formats (audit tool)

  • package.json (npm/yarn/pnpm)
  • requirements.txt, pyproject.toml, Pipfile (Python)
  • go.mod (Go)
  • Cargo.toml (Rust)
  • Gemfile (Ruby)
  • composer.json (PHP)

License

Apache 2.0. See LICENSE and NOTICE.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.