MCP Link: Empowering AI Agents with Real-World Tools 🌐🤖

Created By
10210wkkwa year ago
Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server
Overview

MCP Link is a project that empowers AI agents like ChatGPT and Claude to utilize real-world tools through a browser extension and an optional MCP server, enhancing their capabilities in various tasks.

To use MCP Link, install the browser extension for your preferred browser (Chrome, Firefox, or Safari), approve the tools you want your AI agent to access, and start interacting with your AI agent to perform tasks using those tools.

  • Browser extensions for easy integration with popular browsers.
  • An optional MCP server for enhanced communication.
  • A tool approval system for security and privacy.
  • Semantic search capabilities for quick information retrieval.
  • Docker sandbox for secure testing and deployment.
  • AI automation for repetitive tasks.
  • Integration with various applications to enhance AI functionality.
  1. AI-assisted research for data gathering and report compilation.
  2. Automated customer support using approved tools.
  3. Personal productivity enhancements through task automation.
  • Can I use MCP Link with any AI agent?

Yes! MCP Link is designed to work with AI agents like ChatGPT and Claude.

  • Is the MCP server mandatory?

No, the MCP server is optional but can enhance functionality.

  • How do I ensure the security of my tools?

MCP Link includes a tool approval system that allows you to control which tools your AI agents can access.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
10210wkkw
Star
0
Language
HTML
License
View license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

32 minutes ago