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

Related MCP server: EVIDIQ Clause

Routes

• GET / returns the Home review shell page.

• GET /privacy returns the Privacy page.

• GET /terms returns the Terms page.

• GET /support returns the Support page.

• GET /health returns stable JSON:

{
  "status": "ok",
  "app": "contract-information-extractor",
  "version": "1.0.0"
}

• POST /mcp supports JSON-RPC 2.0 MCP methods.

• GET /.well-known/openai-apps-challenge returns the configured OpenAI apps challenge value as plain text.

MCP Methods

• initialize

• tools/list

• tools/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