Fiber AI

Fiber AI — MCP Server

The 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.

For AI agents

If you are a coding agent and need to pick between MCP and the REST API, start with the canonical agent-facing docs on the API:

• Routing index + critical rules: https://api.fiber.ai/llms.txt
• Per-operation markdown: https://api.fiber.ai/ai-docs/ .md
• Operation index: https://api.fiber.ai/ai-docs/index.md
• MCP walkthrough for LLMs: https://docs.fiber.ai/article/using-mcp-in-llms

Rule of thumb: use MCP when you're acting inside an IDE / chat and each operation is a tool call; use the REST API (via @fiberai/sdk or fiberai) when you're building an autonomous script or a production pipeline.

Servers

Fiber AI offers three remote MCP servers:

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.

Want more than MCP? Use the Fiber AI plugin

The Fiber AI plugin bundles these MCP servers with 16 skills (search, enrich, audiences, recruiting and SDR playbooks) and 7 persona subagents (ai-sdr, ai-recruiter, gtm-strategist, and more) for Claude Code, Cursor, Gemini CLI, OpenCode, Codex, and VS Code. See its install guide. This repo covers the MCP servers only.

---

Setup

Get an API key at fiber.ai/app/api for V2 and Core. The examples read it from a FIBER_API_KEY environment variable. V3 needs no key: your client opens a browser for SSO login on first connect.

Connect directly with the config for your client below, or through Smithery.

Smithery

Fiber AI is listed on Smithery as fiberai/fiber-mcp (V2) and fiberai/fiber-core (Core). Install into your client with one command:

npx -y @smithery/cli@latest mcp add fiberai/fiber-mcp --client cursor

Replace cursor with your client: claude-code, claude, vscode, codex, gemini-cli, windsurf, opencode, cline, goose, and more (npx -y @smithery/cli@latest mcp add --help lists them all). Use fiberai/fiber-core for Core. On first connect your client opens Smithery in the browser to sign in and set your Fiber API key.

To use it as a Smithery connection instead (for agents that call tools through the Smithery CLI):

npx -y @smithery/cli@latest mcp add fiberai/fiber-mcp --id fiber-ai-v2 \

--headers "{\"x-api-key\": \"$FIBER_API_KEY\"}" npx -y @smithery/cli@latest tool list fiber-ai-v2

---

Cursor

Paste a link into your browser address bar and press Enter (Cursor must be installed):

V2:

cursor://anysphere.cursor-deeplink/mcp/install?name=fiber-ai-v2&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmZpYmVyLmFpL21jcC92MiJ9

V3 (OAuth):

cursor://anysphere.cursor-deeplink/mcp/install?name=fiber-ai-v3&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmZpYmVyLmFpL21jcC92MyJ9

Core:

cursor://anysphere.cursor-deeplink/mcp/install?name=fiber-ai-core&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmZpYmVyLmFpL21jcCJ9

The links don't include your key; give it to the agent in chat, or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in your project):

{

"mcpServers": { "fiber-ai-v2": { "type": "http", "url": "https://mcp.fiber.ai/mcp/v2", "headers": { "x-api-key": "${env:FIBER_API_KEY}" } }, "fiber-ai-v3": { "type": "http", "url": "https://mcp.fiber.ai/mcp/v3" }, "fiber-ai-core": { "type": "http", "url": "https://mcp.fiber.ai/mcp", "headers": { "x-api-key": "${env:FIBER_API_KEY}" } } } }

---

Claude Code

claude mcp add --transport http fiber-ai-v2 https://mcp.fiber.ai/mcp/v2 \

--header "x-api-key: $FIBER_API_KEY"

claude mcp add --transport http fiber-ai-v3 https://mcp.fiber.ai/mcp/v3

claude mcp add --transport http fiber-ai-core https://mcp.fiber.ai/mcp \ --header "x-api-key: $FIBER_API_KEY"

Run /mcp inside a Claude Code session to verify the connection and complete the V3 login.

---

Claude Desktop and claude.ai

Claude Desktop and claude.ai add remote servers as custom connectors, which authenticate with OAuth and can't send an API-key header. Use V3:

1. Open Settings → Connectors → Add custom connector.
2. Enter https://mcp.fiber.ai/mcp/v3 and sign in when prompted.

You can also add https://mcp.fiber.ai/mcp/v2 as a connector and give the agent your key in chat (see Authentication).

---

Codex

Add to ~/.codex/config.toml:

[mcp_servers.fiber-ai-v2]

url = "https://mcp.fiber.ai/mcp/v2" env_http_headers = { "x-api-key" = "FIBER_API_KEY" }

[mcp_servers.fiber-ai-v3] url = "https://mcp.fiber.ai/mcp/v3"

[mcp_servers.fiber-ai-core] url = "https://mcp.fiber.ai/mcp" env_http_headers = { "x-api-key" = "FIBER_API_KEY" }

env_http_headers sends the value of the FIBER_API_KEY environment variable as the x-api-key header. Then sign in to V3:

codex mcp login fiber-ai-v3

The Codex IDE extension and the Codex app read the same ~/.codex/config.toml.

---

Gemini CLI

gemini mcp add -t http -H "x-api-key: $FIBER_API_KEY" fiber-ai-v2 https://mcp.fiber.ai/mcp/v2

gemini mcp add -t http fiber-ai-v3 https://mcp.fiber.ai/mcp/v3 gemini mcp add -t http -H "x-api-key: $FIBER_API_KEY" fiber-ai-core https://mcp.fiber.ai/mcp

Add -s user to install for every project instead of the current one. Run gemini mcp list to verify, and /mcp auth fiber-ai-v3 inside a session to sign in to V3.

---

OpenCode

Add to opencode.json in your project (or ~/.config/opencode/opencode.json):

{

"$schema": "https://opencode.ai/config.json", "mcp": { "fiber-ai-v2": { "type": "remote", "url": "https://mcp.fiber.ai/mcp/v2", "headers": { "x-api-key": "{env:FIBER_API_KEY}" } }, "fiber-ai-v3": { "type": "remote", "url": "https://mcp.fiber.ai/mcp/v3" }, "fiber-ai-core": { "type": "remote", "url": "https://mcp.fiber.ai/mcp", "headers": { "x-api-key": "{env:FIBER_API_KEY}" } } } }

Run opencode mcp list to verify, and opencode mcp auth fiber-ai-v3 to sign in to V3.

---

Visual Studio Code

Add to .vscode/mcp.json in your workspace (VS Code reads servers from the top-level servers key):

{

"inputs": [ { "type": "promptString", "id": "fiber-api-key", "description": "Fiber AI API key", "password": true } ], "servers": { "fiber-ai-v2": { "type": "http", "url": "https://mcp.fiber.ai/mcp/v2", "headers": { "x-api-key": "${input:fiber-api-key}" } }, "fiber-ai-v3": { "type": "http", "url": "https://mcp.fiber.ai/mcp/v3" }, "fiber-ai-core": { "type": "http", "url": "https://mcp.fiber.ai/mcp", "headers": { "x-api-key": "${input:fiber-api-key}" } } } }

VS Code prompts for the key once and stores it securely. Start the servers from MCP: List Servers.

---

Windsurf (Devin Desktop)

Open the Cascade panel's ... menu → Open MCP config file, and add:

{

"mcpServers": { "fiber-ai-v2": { "serverUrl": "https://mcp.fiber.ai/mcp/v2", "headers": { "x-api-key": "${env:FIBER_API_KEY}" } }, "fiber-ai-v3": { "serverUrl": "https://mcp.fiber.ai/mcp/v3" }, "fiber-ai-core": { "serverUrl": "https://mcp.fiber.ai/mcp", "headers": { "x-api-key": "${env:FIBER_API_KEY}" } } } }

---

Zed

Open Settings → AI → MCP Servers → Add Server → Add Remote Server, or add to your settings file:

{

"context_servers": { "fiber-ai-v2": { "url": "https://mcp.fiber.ai/mcp/v2", "headers": { "Authorization": "Bearer sk_live_..." } }, "fiber-ai-v3": { "url": "https://mcp.fiber.ai/mcp/v3" }, "fiber-ai-core": { "url": "https://mcp.fiber.ai/mcp", "headers": { "Authorization": "Bearer sk_live_..." } } } }

Zed starts an OAuth login for any remote server without an Authorization header, so use the Bearer form for V2 and Core.

---

Others

Most MCP-compatible tools can be configured with:

• URL: https://mcp.fiber.ai/mcp/v2 (or /mcp/v3, /mcp)
• Transport: HTTP (Streamable HTTP)
• Auth: header x-api-key: (or Authorization: Bearer ) for V2 and Core; OAuth for V3
• For stdio-only clients: npx -y mcp-remote https://mcp.fiber.ai/mcp/v2 --header x-api-key:$FIBER_API_KEY

---

Available Tools

V2 Server (/mcp/v2)

Direct API tools — each Fiber AI endpoint is exposed as an individual tool:

V3 Server (/mcp/v3)

One direct tool per public operation (100+), with compact descriptions the model can expand on demand.

Core Server (/mcp)

Meta tools for dynamic endpoint discovery:

---

Authentication

V2 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.

You can supply your key in any of these three ways - pick whichever your client makes easiest:

Option A - via chat (zero config)

The agent passes the key in the request body as apiKey. Simplest path: paste your key into the agent