{
  "markdown": "# Fiber AI — MCP Server\n\nThe Model Context Protocol (MCP) server provides a standardized interface that allows any compatible AI agent to access Fiber AI's data and tools — search companies, enrich contacts, reveal emails, and more — directly from your editor.\n\n## For AI agents\n\nIf you are a coding agent and need to pick between MCP and the REST API,\nstart with the canonical agent-facing docs on the API:\n\n- **Routing index + critical rules:** https://api.fiber.ai/llms.txt\n- **Per-operation markdown:** `https://api.fiber.ai/ai-docs/<operationId>.md`\n- **Operation index:** https://api.fiber.ai/ai-docs/index.md\n- **MCP walkthrough for LLMs:** https://docs.fiber.ai/article/using-mcp-in-llms\n\nRule of thumb: use **MCP** when you're acting inside an IDE / chat and\neach operation is a tool call; use the **REST API** (via\n[`@fiberai/sdk`](https://github.com/fiber-ai/typescript-sdk) or\n[`fiberai`](https://github.com/fiber-ai/python-sdk)) when you're building\nan autonomous script or a production pipeline.\n\n## Servers\n\nFiber AI offers three remote MCP servers:\n\n| Server | URL | Auth | Best For |\n|--------|-----|------|----------|\n| **V2** | `https://mcp.fiber.ai/mcp/v2` | API key | Auto-generated direct tools for the top ~10 priority operations (`api_companySearch`, `api_peopleSearch`, etc.) |\n| **V3** | `https://mcp.fiber.ai/mcp/v3` | OAuth (SSO) | Direct tools for every public operation with compact descriptions; the model can call or expand any tool on demand |\n| **Core** | `https://mcp.fiber.ai/mcp` | API key | 5 meta-tools that discover and call any of 100+ API endpoints (`search_endpoints`, `list_tag_packs`, `list_all_endpoints`, `get_endpoint_details_full`, `call_operation`) |\n\n> **Which one should I use?** **V2** is the fastest path for the most common flows with an API key. **V3** is the most ergonomic for broad agent coverage — it exposes every public operation as a direct tool with compact descriptions, authenticated via browser-based SSO login instead of a pasted key. **Core** keeps the tool count tiny (5) and lets the agent discover endpoints at runtime; it uses the same API-key auth as V2. You can register more than one; the server names (`fiber-ai-v2`, `fiber-ai-v3`, `fiber-ai-core`) stay distinct.\n\n---\n\n## Setup\n\n### Smithery\n\nInstall via [Smithery](https://smithery.ai) with a single command:\n\n```bash\nnpx -y @smithery/cli install @fiber-ai/mcp --client cursor\n```\n\nReplace `cursor` with your client: `claude`, `windsurf`, `vscode`, `zed`, etc.\n\nOr browse and install from the Smithery web UI at [smithery.ai/server/@fiber-ai/mcp](https://smithery.ai/server/@fiber-ai/mcp).\n\n---\n\n### Cursor\n\nClick the link below to install automatically — paste it into your browser address bar and press Enter:\n\n**Install V2:**\n\n```\ncursor://anysphere.cursor-deeplink/mcp/install?name=FiberAI-V2&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AvdjIifQ==\n```\n\n**Install Core:**\n\n```\ncursor://anysphere.cursor-deeplink/mcp/install?name=FiberAI&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AifQ==\n```\n\nOr manually: open Cursor Settings → Features → MCP → \"+ Add New MCP Server\" → Type: `HTTP` → URL: `https://mcp.fiber.ai/mcp/v2`\n\n---\n\n### Claude Code\n\nThe simplest path passes your key as a header so the agent never sees it in chat:\n\n```bash\nclaude mcp add --transport http fiber-ai-v2 https://mcp.fiber.ai/mcp/v2 \\\n  --header \"x-api-key: $FIBER_API_KEY\"\n```\n\nTo also add the Core server:\n\n```bash\nclaude mcp add --transport http fiber-ai https://mcp.fiber.ai/mcp \\\n  --header \"x-api-key: $FIBER_API_KEY\"\n```\n\nOr, if you prefer to give the key via chat, drop the `--header` flag and the agent will pass `apiKey` in the request body when you tell it your key.\n\nRun `/mcp` inside a Claude Code session to verify the connection.\n\n---\n\n### Claude Desktop\n\nFrom Claude settings → Connectors, add a new MCP server with the URL `https://mcp.fiber.ai/mcp/v2`.\n\nOr edit your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"fiber-ai-v2\": {\n      \"url\": \"https://mcp.fiber.ai/mcp/v2\",\n      \"transport\": { \"type\": \"http\" },\n      \"headers\": { \"x-api-key\": \"sk_live_...\" }\n    },\n    \"fiber-ai\": {\n      \"url\": \"https://mcp.fiber.ai/mcp\",\n      \"transport\": { \"type\": \"http\" },\n      \"headers\": { \"x-api-key\": \"sk_live_...\" }\n    }\n  }\n}\n```\n\nThe `headers` field is optional - if you omit it, the agent will pass `apiKey` in the request body when you give it your key in chat.\n\n---\n\n### Codex\n\n```bash\ncodex mcp add fiber-ai --url https://mcp.fiber.ai/mcp/v2\n```\n\nOr add to `~/.codex/config.toml`:\n\n```toml\n[mcp_servers.fiber-ai]\nurl = \"https://mcp.fiber.ai/mcp/v2\"\ntransport = \"http\"\n\n[mcp_servers.fiber-ai.headers]\nx-api-key = \"sk_live_...\"\n```\n\nThe `[mcp_servers.fiber-ai.headers]` block is optional - drop it and give the key in chat instead.\n\n---\n\n### Visual Studio Code\n\nPress `Ctrl/Cmd + P`, search for **MCP: Add Server**, select **Command (stdio)**, and enter:\n\n```\nnpx mcp-remote https://mcp.fiber.ai/mcp/v2\n```\n\nName it `FiberAI` and activate it via **MCP: List Servers**.\n\nOr add to `.vscode/mcp.json`. If your VS Code version supports HTTP MCP natively, prefer the header-based shape:\n\n```json\n{\n  \"mcpServers\": {\n    \"fiber-ai\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.fiber.ai/mcp/v2\",\n      \"headers\": { \"x-api-key\": \"${env:FIBER_API_KEY}\" }\n    }\n  }\n}\n```\n\nOlder VS Code releases need the stdio wrapper (`mcp-remote` forwards your `FIBER_API_KEY` env var as a header):\n\n```json\n{\n  \"mcpServers\": {\n    \"fiber-ai\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"mcp-remote\",\n        \"https://mcp.fiber.ai/mcp/v2\",\n        \"--header\",\n        \"x-api-key:${FIBER_API_KEY}\"\n      ]\n    }\n  }\n}\n```\n\n---\n\n### Windsurf\n\nPress `Ctrl/Cmd + ,` → Cascade → MCP servers → Add custom server:\n\n```json\n{\n  \"mcpServers\": {\n    \"fiber-ai\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"mcp-remote\",\n        \"https://mcp.fiber.ai/mcp/v2\",\n        \"--header\",\n        \"x-api-key:${FIBER_API_KEY}\"\n      ]\n    }\n  }\n}\n```\n\n---\n\n### Zed\n\nPress `Cmd + ,` and add:\n\n```json\n{\n  \"context_servers\": {\n    \"fiber-ai\": {\n      \"source\": \"custom\",\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"mcp-remote\",\n        \"https://mcp.fiber.ai/mcp/v2\",\n        \"--header\",\n        \"x-api-key:${FIBER_API_KEY}\"\n      ],\n      \"env\": { \"FIBER_API_KEY\": \"sk_live_...\" }\n    }\n  }\n}\n```\n\n---\n\n### Others\n\nMost MCP-compatible tools can be configured with:\n\n- **URL**: `https://mcp.fiber.ai/mcp/v2`\n- **Transport**: HTTP (Streamable HTTP)\n- **Auth**: header `x-api-key: <your key>` (or `Authorization: Bearer <your key>`)\n- For stdio-only clients: `npx -y mcp-remote https://mcp.fiber.ai/mcp/v2 --header x-api-key:$FIBER_API_KEY`\n\n---\n\n## Available Tools\n\n### V2 Server (`/mcp/v2/`)\n\nDirect API tools — each Fiber AI endpoint is exposed as an individual tool:\n\n| Tool | Description |\n|------|-------------|\n| `api_companySearch` | Search for companies by industry, location, size, funding, etc. |\n| `api_peopleSearch` | Search for people by title, seniority, department, etc. |\n| `api_individualRevealSync` | Reveal work email and phone for a LinkedIn profile |\n| `api_companyLiveFetch` | Get live LinkedIn data for a company |\n| `api_personLiveFetch` | Get live LinkedIn data for a person |\n| `api_getOrgCredits` | Check your credit balance |\n\n### Core Server (`/mcp`)\n\nMeta tools for dynamic endpoint discovery:\n\n| Tool | Description |\n|------|-------------|\n| `search_endpoints` | Search for API endpoints by keyword |\n| `list_all_endpoints` | List all available API endpoints |\n| `get_endpoint_details_full` | Get full schema details for an endpoint |\n| `call_operation` | Call any API endpoint by its operation ID |\n\n---\n\n## Authentication\n\nV2 and Core require a Fiber AI API key. V3 uses OAuth (Clerk SSO) - the client opens a browser window for login and reuses the session token, no key configuration needed. Get an API key at [fiber.ai/app/api](https://fiber.ai/app/api).\n\nYou can supply your key in **any** of these three ways - pick whichever your client makes easiest:\n\n### Option A - via chat (zero config)\n\nThe agent passes the key in the request body as `apiKey`. Simplest path: paste your key into the agent once and it'll keep using it.\n\n```\nYou:    Use sk_live_... as my Fiber API key.\nAgent:  [calls api_companySearch with { \"apiKey\": \"sk_live_...\", \"searchParams\": {...} }]\n```\n\nCaveat: the key ends up in chat history. Fine for personal use, not ideal for shared sessions.\n\n### Option B - via `x-api-key` header (recommended for IDEs)\n\nConfigure the header once in your MCP client config; the agent never sees the key.\n\n```json\n{\n  \"mcpServers\": {\n    \"fiber-ai-v2\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.fiber.ai/mcp/v2\",\n      \"headers\": { \"x-api-key\": \"sk_live_...\" }\n    },\n    \"fiber-ai-core\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.fiber.ai/mcp\",\n      \"headers\": { \"x-api-key\": \"sk_live_...\" }\n    }\n  }\n}\n```\n\nMost clients (Claude Code, Cursor, Claude Desktop, Codex, Windsurf, VS Code) accept a `headers` field on each MCP server. Reference your env var instead of hard-coding:\n\n```json\n\"headers\": { \"x-api-key\": \"${env:FIBER_API_KEY}\" }\n```\n\n### Option C - via `Authorization: Bearer` header\n\nSame shape as Option B, but using the standard bearer-token header. Useful if your MCP client only supports `Authorization`-style auth.\n\n```json\n\"headers\": { \"Authorization\": \"Bearer sk_live_...\" }\n```\n\n### Resolution order\n\nWhen more than one is present, the server resolves in this order: body/query `apiKey` -> `x-api-key` header -> `Authorization: Bearer`. The first non-empty value wins.\n\n### V3 (OAuth)\n\nV3 ignores all of the above. On first connect, the client opens `https://app.fiber.ai` for browser-based SSO login; the resulting session token is reused on subsequent calls. No env vars, no headers, no config to write.\n\n---\n\n## Example Usage\n\nOnce connected, ask your AI agent:\n\n- *\"Search for SaaS companies in New York with 50-200 employees\"*\n- *\"Find the CEO of <a company you care about> and get their work email\"*\n- *\"How many credits do I have left?\"*\n- *\"Enrich this LinkedIn profile: linkedin.com/in/...\"*\n\n---\n\n## SDKs\n\nFor building applications programmatically (not via MCP):\n\n- **TypeScript**: `npm install @fiberai/sdk` — [GitHub](https://github.com/fiber-ai/typescript-sdk)\n- **Python**: `pip install fiberai` — [GitHub](https://github.com/fiber-ai/python-sdk)\n\n---\n\n## FAQ\n\n**Connection not working?**\nEnsure your editor supports HTTP (Streamable HTTP) MCP transport. If it only supports stdio, use the `npx mcp-remote` wrapper shown in the VS Code / Windsurf / Zed instructions.\n\n**Getting authentication errors?**\nMake sure you're supplying a valid key via one of the three supported paths (body `apiKey`, `x-api-key` header, or `Authorization: Bearer`). See [Authentication](#authentication) above. Get a key at [fiber.ai/app/api](https://fiber.ai/app/api).\n\n**Should I put the key in chat or in headers?**\nFor personal sessions, chat is fine. For shared sessions, team-config files committed to git, or anywhere chat history might leak, configure the `x-api-key` header at the MCP client layer so the agent never sees the raw key.\n\n**Can I use both servers at the same time?**\nYes. Many users add both V2 and Core for maximum flexibility.\n\n---\n\n## License\n\nMIT\n",
  "bytes": 11320,
  "sha": "d53da42692c50c9e651660d3aa28fa097db08ab620b44a935222ed9bc62d45b0",
  "repo_slug": "fiber-ai/mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_fiber_mcp_7d3a1d9a/readme"
}