docfork
Verified Safeby docfork
Overview
Provides AI agents with up-to-date, curated technical documentation to prevent hallucinations and ensure current API usage.
Installation
npx -y docfork --api-key YOUR_API_KEYEnvironment Variables
- API_URL
- CLIENT_IP_ENCRYPTION_KEY
- DOCFORK_API_KEY
- DOCFORK_CABINET
- DEFAULT_MINIMUM_TOKENS
- PORT
- MCP_TRANSPORT
Security Notes
The server demonstrates good security practices including explicit API key authentication, validation for cabinet usage, and optional AES-256-CBC encryption for client IP addresses. Authentication context is managed per request using AsyncLocalStorage to prevent credential leakage. Input validation is performed using Zod schemas for tool arguments. The server acts as a proxy to an external Docfork API, and no direct code execution or 'eval' statements were found. Broad CORS headers are set, which is common for public APIs but could be more restrictive if client origins are known.
Similar Servers
context7
The Context7 MCP server provides up-to-date, version-specific documentation and code examples from source repositories directly into LLM prompts to improve AI coding assistance.
mcp
Provides AI assistants with direct, secure access to the latest official Microsoft documentation to prevent hallucinations and verify code.
docs-mcp-server
Indexes documentation from various sources (web, local files, package registries) into vector embeddings, enabling semantic search and context retrieval for AI coding assistants via CLI, web UI, or Model Context Protocol (MCP).
chunkhound
Local-first codebase intelligence tool for AI assistants, extracting architecture, patterns, and institutional knowledge at any scale via Model Context Protocol (MCP).