Contract Information Extractor
Enables extracting explicitly stated contract metadata, clauses, and obligations from user-supplied contract text without storing or modifying the data.
README
Contract Information Extractor
App Name: Contract Information Extractor
App Slug: contract-information-extractor
Version: 1.0.0
Support Email: sidcraigau@gmail.com
Contract Information Extractor is a read-only, stateless Cloudflare Workers MCP server for organizing explicitly stated information from user-supplied contract text. It does not store contract text, does not use login, OAuth, a database, external APIs, model APIs, file upload, OCR, PDF parsing, or external write operations.
MCP Endpoint
Production identity endpoint:
https://contract-information-extractor.sidcraigau.workers.dev/mcp
Local development uses:
POST /mcp
Routes
GET /returns the Home review shell page.GET /privacyreturns the Privacy page.GET /termsreturns the Terms page.GET /supportreturns the Support page.GET /healthreturns stable JSON:
{
"status": "ok",
"app": "contract-information-extractor",
"version": "1.0.0"
}
POST /mcpsupports JSON-RPC 2.0 MCP methods.GET /.well-known/openai-apps-challengereturns the configured OpenAI apps challenge value as plain text.
MCP Methods
initializetools/listtools/call
Tools
extract_contract_metadata: extracts explicitly stated contract type, parties, effective date, expiration date, contract value, payment terms, and governing law.extract_contract_clauses: extracts explicitly present payment, termination, confidentiality, liability, intellectual property, and delivery clauses.extract_contract_obligations: organizes explicitly stated parties, obligations, deliverables, deadlines, and dependencies.
All tools share the same input shape:
{
"contract_text": "The complete or partial contract text supplied by the user.",
"request_intent": "Optional requested action description."
}
contract_text is required and must be a non-empty string at runtime. request_intent is optional and is used only to reject requests outside the extraction scope.
Each tool returns structuredContent matching its outputSchema. Successful partial extraction is still status: "success"; unavailable fields are empty strings or empty arrays and are listed in missing_fields.
Scope Boundaries
This app only extracts information directly supported by the supplied plain text. It does not provide legal advice and does not judge contract legality, validity, enforceability, breach, fairness, risk, or which party has greater responsibility. It does not recommend, modify, rewrite, draft, submit, send, save, or negotiate contract terms.
The current version accepts only plain text in contract_text.
Local Development
Install dependencies:
npm install
Run the Worker locally:
npm run dev
Run type checks:
npm run typecheck
Run all automated tests:
npm test
Run MCP route regression tests:
npm run test:mcp:local
Run production route and MCP regression tests after deployment:
npm run test:mcp:production
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.