{
  "markdown": "# ToolHail\n\n**The discovery-and-payment layer for AI agents.** ToolHail lets an AI agent find the right [MCP](https://modelcontextprotocol.io) (Model Context Protocol) server for any task and call it — paying per use — without installing anything.\n\nThere are 10,000+ MCP servers an agent could use, and no good way to discover and use one *mid-task*. ToolHail closes that gap with two tools:\n\n- 🔎 **`find_mcp_server`** *(free)* — describe a capability in plain language (`\"query a Postgres database\"`, `\"send a Slack message\"`, `\"scrape a web page\"`) and get ranked, deduplicated MCP servers from every major registry (mcp.so, PulseMCP, Smithery, Glama) with ready-to-paste setup.\n- ⚡ **`call_tool`** *(paid)* — invoke a discovered remote MCP server through ToolHail's SSRF-guarded proxy. No install, one hop; each successful call is metered and billed through Stripe.\n\n## Use it\n\n**Hosted MCP endpoint** (Streamable HTTP):\n\n```\nhttps://mcp.toolhail.com/mcp\n```\n\nAdd it to Claude Code (or any MCP client):\n\n```bash\nclaude mcp add --transport http toolhail https://mcp.toolhail.com/mcp\n```\n\n**MCP Scout on the Apify Store** — the discovery engine as a standalone, pay-per-search actor:\nhttps://apify.com/01010101/mcp-scout\n\n**Site:** https://toolhail.com · **Guide:** https://toolhail.com/guide\n\n## How it works\n\n1. **Discover** — the agent hits a capability gap and asks `find_mcp_server`, which searches the registries and returns the best-fit servers, ranked for usability.\n2. **Execute** — instead of installing, the agent calls the chosen tool via `call_tool`; ToolHail proxies it in one hop, nothing to configure.\n3. **Settle** — each successful call is metered and billed through Stripe. The agent pays for exactly what it used.\n\n## Why it exists\n\nAn agent's toolset is fixed at configuration time, but real tasks need capabilities the agent doesn't have. Today the options are \"hard-code every server you might ever need\" or \"give up.\" ToolHail makes tools a **runtime resource**: discovered on demand, called through one endpoint, paid per use. It is discovery *and* payment infrastructure for the agentic web — built entirely on the open Model Context Protocol.\n\n## Repo layout\n\n| Path | What |\n|------|------|\n| [`apify-mcp-scout/`](apify-mcp-scout/) | MCP Scout — the discovery engine, published on the Apify Store (**live**) |\n| [`gateway-worker/`](gateway-worker/) | Hosted MCP gateway on Cloudflare Workers — `find_mcp_server` + `call_tool` (**live** at `mcp.toolhail.com`) |\n| [`gateway/`](gateway/) | Reference gateway + Stripe metering + tests |\n| [`landing/`](landing/) | `toolhail.com` site (landing + guide + `llms.txt`) |\n| [`registry/`](registry/) | MCP registry listing metadata (`server.json`) + submission playbook |\n| [`dashboard/`](dashboard/) | Private revenue/usage dashboard |\n| [`brand/`](brand/) | Brand assets |\n\n## Built on\n\nModel Context Protocol · Cloudflare Workers · Stripe · Apify\n",
  "bytes": 2921,
  "sha": "661486c2723988cb7bc2a9a13b4a20c23dab9b981fdc938a23245be725204869",
  "repo_slug": "toolhail/toolbroker",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_toolhail_gateway_67093873/readme"
}