Fineprint MCP Server
OfficialThis server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Fineprint MCP Server
The pre-commit hook for agents. Never accept terms unread.
This repository contains the MCP server implementation for Fineprint, the terms-of-service risk API for AI agents. The server scans a service's terms before an agent accepts them — signups, subscriptions, vendor agreements — and returns a 0–100 risk score, a pass/flag/block verdict, an agent-friendliness verdict (does the ToS even allow agents?), and every clause anchored to a verbatim quote.
The MCP server
Implementation:
mcp/mcp_server.py— a FastMCP (Python) server exposing 13 tools covering scans by URL or text, agent-access checks, the public leaderboard, scan retrieval and PDF reports, monitors, and policy evaluation.Container:
mcp/Dockerfile; published imageghcr.io/fineprintcorp/fineprint-mcp— also listed in the official MCP Registry asio.github.fineprintcorp/fineprint(seeserver.json).Config:
FINEPRINT_API_URL(defaults to the production API) andFINEPRINT_API_KEY(free key from the API signup; free tier is 25 scans/mo).
Run it locally:
cd mcp
FINEPRINT_API_KEY=<your key> python mcp_server.pyClaude Code:
claude mcp add fineprint --env FINEPRINT_API_KEY=<your key> -- python mcp/mcp_server.pyOr run the published container image — server.json carries the exact
package and environment declaration.
Related MCP server: jev-legal-clause-mcp
The agent skill
The repository also ships a skill that teaches an agent when to call the server:
The rule: if you're about to accept terms, create an account, or subscribe to a service — scan first, then decide.
Check agent-friendliness first:
hostilemeans the ToS bans bots/automated access — and the violation lands on the user, not the agent. Treat likeblock.Verdict handling:
pass→ proceed ·flag→ surface clauses to the user ·block→ stop and ask.Three ways to scan: MCP server, REST API (free key, 25 scans/mo), or x402 pay-per-scan ($0.25, no signup; settlement being enabled).
Check the free leaderboard first before spending a scan.
Install the skill:
npx skills add fineprintcorp/fineprint-skill --skill fineprint -gFull skill text: SKILL.md. A zero-key demo lives in demo/.
License
MIT (see LICENSE).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Scan text, documents, websites, and MCP metadata for prompt injection and sensitive-data risks.
Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.
Check what AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot) receive from any website, graded A to F, and get a signed, offline-verifiable verdict before an agent reads, cites, connects to or buys from a site. Covers robots.txt and content rights, site safety, MCP server checks and crawler-log verification.
Qualified human outcomes for AI agents: attorney review of SaaS Terms/Privacy, on-site checks.
Related MCP Servers
- AlicenseAqualityDmaintenanceURL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.1664 npm1MIT
- AlicenseAqualityCmaintenanceEnables agents to analyze contract excerpts and receive calibrated risk annotations across 10 default risk classes, including presence probabilities, overall risk levels, and human review recommendations.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables scanning of enterprise MSAs, NDAs, and vendor SOWs to detect high-risk clauses such as unlimited indemnity, one-sided IP assignment, perpetual non-compete, and evergreen auto-renewal traps. Computes composite risk scores with an overall contract health rating and generates precise legal redlines and executive memos.7MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables users to scan enterprise MSAs, NDAs, and Vendor SOWs in Tencent Docs for high-risk clauses such as unlimited indemnity, one-sided IP assignment, perpetual non-compete, and evergreen auto-renewal traps; calculates composite risk scores and generates precise legal redlines.MIT