mcpField
M
mcp-check-licenses

mcp-check-licenses

Local
github.com/webmoleaiLegal & Government1Updated 29w ago

About mcp-check-licenses

mcp-check-licenses is an MCP server that checks npm dependency licenses in a supplied `package.json` and reports compatibility risks. It is intended for project maintainers reviewing license obligations, with classifications for common license groups and flags for GPL/AGPL conflicts.

Key features

  1. 01Parse dependencies and devDependencies
  2. 02Fetch license data from npm
  3. 03Classify common license types
  4. 04Flag license compatibility conflicts
  5. 05Return structured risk reports

Use cases

  1. 01Review licenses before a project release
  2. 02Check for GPL or AGPL dependencies
  3. 03Summarize unknown package licenses

MCP support

The MCP server provides an `audit-licenses` tool that accepts `packageJson` contents and returns a JSON report with analyzed packages, license classifications, and a risk level.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"webmoleai-mcp-check-licenses": {
"command": "npx",
"args": [
"-y",
"mcp-check-licenses"
]
}
}
}
Run commandnpx -y mcp-check-licenses

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
npmmcp-check-licenses0.2.0

Tools

1

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
packageJsonstringYesContents of a package.json file as a string

Details

From the project README

mcp-license-audit

MCP server that audits your project's dependency licenses for compatibility issues. Flags GPL/AGPL conflicts and generates compliance reports.

What It Does

  • Parses a package.json file (dependencies + devDependencies)
  • Fetches license info for each package from the npm registry
  • Classifies licenses: permissive (MIT, Apache, BSD, ISC), copyleft (GPL, AGPL), weak-copyleft (LGPL, MPL), unknown
  • Detects conflicts (e.g., GPL dependency in an MIT-licensed project)
  • Returns a structured JSON report with risk level and summary

Install

npm install -g mcp-license-audit
# or run directly:
npx mcp-license-audit

Configure in Claude Code

Add to your .claude/mcp.json or ~/.claude/mcp.json:

{
  "mcpServers": {
    "license-audit": {
      "command": "npx",
      "args": ["mcp-license-audit"]
    }
  }
}

Or if installed globally:

{
  "mcpServers": {
    "license-audit": {
      "command": "mcp-license-audit"
    }
  }
}

Analytics

This server supports MCPcat analytics. To enable usage tracking, session replay, and error monitoring, set the MCPCAT_PROJECT_ID environment variable in your MCP client config:

{
  "mcpServers": {
    "license-audit": {
      "command": "npx",
      "args": ["mcp-license-audit"],
      "env": {
        "MCPCAT_PROJECT_ID": "proj_your_id_here"
      }
    }
  }
}

Without it, the server runs normally with no analytics. See the MCPcat setup guide for details.

Tool: audit-licenses

Input: packageJson — the full contents of a package.json file as a string.

Output: JSON report:

{
  "totalDependencies": 15,
  "analyzed": 15,
  "licenses": {
    "MIT": ["express", "lodash"],
    "Apache-2.0": ["typescript"],
    "GPL-3.0": ["some-package"],
    "unknown": ["private-pkg"]
  },
  "conflicts": [
    {
      "package": "some-package",
      "license": "GPL-3.0",
      "issue": "GPL dependency in MIT project — must open-source your code if distributed"
    }
  ],
  "riskLevel": "medium",
  "summary": "15 deps analyzed. 1 GPL conflict found. 1 unknown license."
}

Risk levels: low (no copyleft), medium (weak copyleft or many unknowns), high (GPL/AGPL found).

Limits

  • Analyzes first 20 dependencies for speed
  • Only supports npm packages (no pip/cargo/gem support yet)
  • License data comes from the npm registry — private packages return "unknown"

Build from Source

npm install
npm run build
node dist/index.js

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.