{
  "markdown": "# Giggal.ai MCP Server\n\n[Available on Smithery](https://smithery.ai/servers/hassaanali723/giggal)\n\nVerify catch-all, accept-all, and SEG-protected email addresses without leaving Claude, ChatGPT, Cursor, VS Code, or any other MCP client. This is the official [Model Context Protocol](https://modelcontextprotocol.io) server for [Giggal.ai](https://giggal.ai), the catch-all email verification tool that confirms the mailboxes other verifiers write off as \"risky\" or \"unknown.\"\n\n```\nMCP URL:  https://mcp.giggal.ai/mcp\n```\n\n## Why Giggal.ai\n\nMost tools give up on the hard addresses. Giggal.ai runs a deep mailbox existence check over SMTP and returns a real deliverability result where others cannot:\n\n- **Catch-all and accept-all domains** that accept every address, even for users who do not exist\n- **SEG-protected inboxes** behind Proofpoint, Mimecast, and Barracuda that block the checks most verifiers rely on\n- **Risky B2B contacts** that competitors flag and discard, around 30% of a typical list, recovered as deliverable\n\n99% accuracy on standard business lists and bounce rates under 3%, straight from your AI assistant.\n\n## Get an API key\n\nSign up at [emailverifier.giggal.ai](https://emailverifier.giggal.ai/sign-up) for **1,000 free verification credits, no card required**, then copy your key from the **Developer API** tab. Claude and ChatGPT connect over OAuth and need no key. The IDE and CLI clients below use the key as a `Bearer` token.\n\n## Connect your AI client\n\n### Claude\n\nAdd Giggal.ai as a custom connector. No config files, no API key.\n\n1. Open **Settings → Connectors** (web or desktop).\n2. Click **Add → Add custom connector**.\n3. Name it **Giggal.ai**, paste the MCP URL, then click **Add**.\n4. Open the **Giggal.ai** connector and click **Connect**.\n5. Click **Allow** to grant `verify:read` (verify addresses, check credits, look up past verifications).\n\n### ChatGPT\n\nAdd Giggal.ai as a custom plugin, connected over OAuth.\n\n1. Open **Plugins** from the sidebar, then click the **+** in the top right.\n2. Name it **Giggal.ai**, set **Server URL** to the MCP URL, choose **Authentication → OAuth**, tick the confirmation, then click **Create**.\n3. Open the plugin, click **Connect**, then **Sign in with Giggal.ai**.\n4. Click **Allow** to grant `verify:read`.\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http --scope user giggal \\\n  https://mcp.giggal.ai/mcp \\\n  --header \"Authorization: Bearer YOUR_API_KEY\"\n```\n\nAlready have a `giggal` server? Run `claude mcp remove giggal --scope user` first, then re-add.\n\n### Cursor, Windsurf, and Cline\n\nAdd this to your MCP config file:\n\n- Cursor: `~/.cursor/mcp.json` (or `.cursor/mcp.json` per project)\n- Windsurf: `~/.codeium/windsurf/mcp_config.json`\n- Cline: `cline_mcp_settings.json` (open it from the Cline MCP settings)\n\n```json\n{\n  \"mcpServers\": {\n    \"giggal\": {\n      \"url\": \"https://mcp.giggal.ai/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### VS Code\n\nAdd to `.vscode/mcp.json`. VS Code uses `servers` instead of `mcpServers`:\n\n```json\n{\n  \"servers\": {\n    \"giggal\": {\n      \"url\": \"https://mcp.giggal.ai/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Zed\n\nAdd to `~/.config/zed/settings.json`:\n\n```json\n{\n  \"context_servers\": {\n    \"giggal\": {\n      \"source\": \"custom\",\n      \"url\": \"https://mcp.giggal.ai/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n### Codex\n\nAdd to `~/.codex/config.toml`:\n\n```toml\n[mcp_servers.giggal]\nurl = \"https://mcp.giggal.ai/mcp\"\nbearer_token_env_var = \"GIGGAL_API_KEY\"\n```\n\nCodex reads the key from an env var. Set it and reload your shell, then fully quit and reopen Codex:\n\n```bash\necho 'export GIGGAL_API_KEY=\"tp_live_...\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n---\n\nRestart the client after adding, then just ask:\n\n> Is info@giggal.ai deliverable?\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `verify_emails` | Verify a single address or a whole list and get a clear valid or invalid result, including catch-all and accept-all domains other tools give up on |\n| `get_verification_details` | Fetch the full breakdown for a job: per-address status, reason codes, and deliverability scoring |\n| `get_credit_balance` | Check remaining verification credits before a large run |\n\nAll tools are read only.\n\n## What this service does\n\n- Speaks the Model Context Protocol so AI assistants can call the tools above\n- Serves an OpenAPI 3.1 spec so ChatGPT Custom GPTs (GPT Actions) can use it\n- Runs an OAuth 2.1 authorization server so AI clients can authenticate users\n- Wraps the Giggal.ai verification API and never re-implements verification logic\n\n## Run it locally (self-host)\n\nPrefer to run your own instance instead of the hosted server? The `giggal-mcp` command is a small stdio server that calls the public Giggal.ai API with your own Developer API key. No database, no OAuth, nothing to host.\n\n**From source:**\n\n```bash\nnpm install\nnpm run build\nGIGGAL_API_KEY=tp_live_... npm run start:local\n```\n\n**With Docker:**\n\n```bash\ndocker build -t giggal-mcp .\ndocker run -i --rm -e GIGGAL_API_KEY=tp_live_... giggal-mcp\n```\n\n**In an MCP client** (point it at your locally built copy):\n\n```json\n{\n  \"mcpServers\": {\n    \"giggal\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/giggal-mcp/dist/local/index.js\"],\n      \"env\": { \"GIGGAL_API_KEY\": \"tp_live_...\" }\n    }\n  }\n}\n```\n\nSame three tools as the hosted server. `GIGGAL_API_BASE` optionally overrides the API base (defaults to `https://api.giggal.ai/v1`).\n\n## About this repository\n\nThis repo powers both the **hosted** server at `https://mcp.giggal.ai/mcp` (OAuth, zero setup) and the **local** stdio server above (`giggal-mcp`, your own API key). Both expose the same three tools and call the Giggal.ai verification API to do the actual work. It is published for transparency.\n\n## Endpoints\n\nThe hosted server exposes:\n\n- `POST /mcp` MCP JSON-RPC (main protocol endpoint)\n- `GET /mcp` MCP SSE stream (server to client notifications)\n- `GET /openapi.json` OpenAPI 3.1 spec (for GPT Actions)\n- `POST /oauth/register` Dynamic Client Registration (RFC 7591)\n- `GET /oauth/authorize` User consent screen\n- `POST /oauth/token` Access token exchange\n- `POST /oauth/revoke` Revoke a token\n- `GET /.well-known/oauth-authorization-server` Server metadata\n- `GET /health` Health check\n\n## License\n\nMIT. See [LICENSE](./LICENSE).\n",
  "bytes": 6456,
  "sha": "0a06aeaa19a9deddd86eab0d16db2176dd6279b87650f53b4440f0582b304e44",
  "repo_slug": "giggal-ai/giggal-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_hassaanali723_giggal_mcp_1761dcc6/readme"
}