"Scraping Public Documents" matching MCP servers:

Provides deterministic business-day calculations for AI agents, correctly handling country-specific weekends and public holidays.

Open Task Relay provides free, bounded public-good tasks that autonomous AI agents can discover, complete, submit, and independently verify. Its public TypeScript source runs locally with a Cloudflare Workers-compatible runtime and SQLite/D1, exposing MCP over HTTP.

Public MCP server for HiveWallet, enabling agent-native wallets with USDC transfers and HiveDNA 3-proof receipts on Base.

Enables MCP-compatible agents to interact with the Kenwea marketplace through a public HTTP endpoint, supporting authentication, session management, and tools for marketplace search, publishing, and onboarding.

An intelligent document processing system that automatically classifies, extracts information from, and routes business documents using the Model Context Protocol (MCP).

Orchestrates AI agents through structured markdown documents, enabling multi-agent workflows with automatic context injection and workflow management.

Enables an AI agent to interact with MCP tools (fetch URLs, query documents, list files) through a FastAPI server secured with GitHub OAuth 2.0.

This server enables remote job discovery, tailored CV creation, and approval-gated application lifecycle management. It prioritizes safe, factual job applications without authenticated LinkedIn scraping or silent submissions.

Enables MCP-compatible AI agents to execute typed live-app actions over WebSocket, allowing agents to directly interact with real application state without browser automation or scraping.

Remote MCP/API trust gate for AI agents to inspect readiness before performing Korean business workflow operations like vendor onboarding and payment release.

Agent-Level Transaction Safety Oracle. Before an AI agent signs a blockchain transaction, it returns a SAFE/UNSAFE verdict with a SENTINEL Score (AAA-D) and risk flags. Pay-per-call $0.005 USDC via x402 on Base.

Enables sending a shared context with multiple independent questions to TypeSafe's Jev model via the public OpenJEV API, returning typed judgments and probabilities (choice, score, or yes/no) instead of prose.

Bridges Warp's Oz coding agent to any IDE or MCP client (Claude Code, Cursor, Codex), plus native @oz in VS Code Copilot Chat. Cross-platform (macOS/Linux/Windows), independent project using only Warp's documented public oz CLI + MCP interfaces.

Delegate a Cursor task to a real, unattended background OpenCode agent — cheaper model, isolated history — through five small MCP tools.

Give your agent an address: private agent-to-agent messaging, free encrypted file handoffs, and Lightning commerce. Buy, sell, and discover files, data, APIs, and compute on a public marketplace. Non-custodial: buyers pay sellers directly and payment unlocks delivery.

MCP server that connects AI assistants to Leapd, enabling them to launch and manage an AI-run business by creating tasks, deploying sites, and accessing business documents.

Intelligence archive for AI agents. Contribute prompts, workflows, and insights to a permanent, cryptographically verifiable knowledge base. Agents earn public trust scores based on adoption and peer validation.

Cross-device communication between AI agents over the public internet

Reduces Claude's context window costs by automatically summarizing inactive files to their public interfaces using AST parsing, keeping only the full contents of the currently active file.

Public MCP deliberation for AI agents: join, propose, argue, amend, vote, follow topics and invite peers through a Streamable HTTP endpoint. Humans can observe debates and conclusions; rules remain contestable and no model-provider API keys are requested.