Using Fiber via MCP

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.

Fiber AI offers three remote MCP servers. You can register one, two, or all three; the server names stay distinct (fiber-ai-v2, fiber-ai-v3, fiber-ai-core).

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 — every public operation is exposed as a direct tool with compact descriptions, authenticated via browser-based SSO 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.

Setup Instructions

Cursor

Visit one of the links below to install automatically. Copy the link, paste it into your browser address bar, and press Enter.

Install V2 (API key):

cursor://anysphere.cursor-deeplink/mcp/install?name=Fiber-AI-v2&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AvdjIifQ==

Install V3 (OAuth, every public operation):

cursor://anysphere.cursor-deeplink/mcp/install?name=Fiber-AI-v3&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AvdjMifQ==

Install Core (5 meta-tools, API key):

cursor://anysphere.cursor-deeplink/mcp/install?name=Fiber-AI&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AifQ==

Or manually:

1. Open Cursor Settings → Features → MCP.

2. Click + Add New MCP Server.

3. Name: Fiber-AI-v2

4. Type: HTTP

5. URL: https://mcp.fiber.ai/mcp/v2

6. (Optional) Add a header x-api-key with your API key so the agent never sees it in chat.

Claude Code

The simplest path passes your key as a header so it never appears in chat history:

claude mcp add --transport http fiber-ai-v2 https://mcp.fiber.ai/mcp/v2 \
  --header "x-api-key: $FIBER_API_KEY"

To also add the Core server:

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

Or, 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. Run /mcp inside a Claude Code session to verify the connection.

Claude Desktop

From Claude settings → Connectors, add a new MCP server with the URL https://mcp.fiber.ai/mcp/v2.

Or edit your claude_desktop_config.json:

{
  "mcpServers": {
    "fiber-ai-v2": {
      "url": "https://mcp.fiber.ai/mcp/v2",
      "transport": { "type": "http" },
      "headers": { "x-api-key": "sk_live_..." }
    },
    "fiber-ai": {
      "url": "https://mcp.fiber.ai/mcp",
      "transport": { "type": "http" },
      "headers": { "x-api-key": "sk_live_..." }
    }
  }
}

The 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.

Codex

codex mcp add fiber-ai --url https://mcp.fiber.ai/mcp/v2

Or add manually to ~/.codex/config.toml:

[mcp_servers.fiber-ai]
url = "https://mcp.fiber.ai/mcp/v2"
transport = "http"

[mcp_servers.fiber-ai.headers]
x-api-key = "sk_live_..."

The [mcp_servers.fiber-ai.headers] block is optional — drop it and give the key in chat instead.

Visual Studio Code

Press Ctrl/Cmd + P, search for MCP: Add Server, select Command (stdio), and enter:

npx mcp-remote https://mcp.fiber.ai/mcp/v2 --header x-api-key:$FIBER_API_KEY

Name it FiberAI and activate it via MCP: List Servers.

Or add to your .vscode/mcp.json. If your VS Code version supports HTTP MCP natively, prefer the header-based shape:

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

Windsurf

1. Press Ctrl/Cmd + , to open Windsurf settings.

2. Scroll to Cascade → MCP servers.

3. Select Add Server → Add custom server.

4. Add the following:

{
  "mcpServers": {
    "fiber-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.fiber.ai/mcp/v2",
        "--header",
        "x-api-key:${FIBER_API_KEY}"
      ]
    }
  }
}

Zed

Press Cmd + , to open Zed settings and add:

{
  "context_servers": {
    "fiber-ai": {
      "source": "custom",
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.fiber.ai/mcp/v2",
        "--header",
        "x-api-key:${FIBER_API_KEY}"
      ],
      "env": { "FIBER_API_KEY": "sk_live_..." }
    }
  }
}

Others

Most MCP-compatible tools can be configured with:

• URL: https://mcp.fiber.ai/mcp/v2

• Transport: HTTP (Streamable HTTP)

• Auth header: x-api-key: <your key> (or Authorization: Bearer <your key>)

• 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)

Same shape as V2 (one tool per operation), but covers every public Fiber AI operation, not just the curated top ten. Tool descriptions are compact by default; the agent can expand any tool on demand. Authentication is browser-based OAuth (Clerk SSO) — you log in once and the session token is reused.

Core Server (/mcp)

Five meta tools for dynamic endpoint discovery. Same API-key auth as V2.

Authentication

V2 and Core are API-key only. V3 is OAuth only (Clerk SSO) and needs no key configuration. Get your API key at fiber.ai/app/api.

For V2 and Core, 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 once and it'll keep using it for the session.

You:    Use sk_live_... as my Fiber API key.
Agent:  [calls api_companySearch with { "apiKey": "sk_live_...", "searchParams": {...} }]

Caveat: the key ends up in chat history. Fine for personal use, not ideal for shared sessions or anywhere chat history might leak.

Option B — via x-api-key header (recommended for IDEs)

Configure the header once in your MCP client config. The agent never sees the raw key.

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

Reference an env var instead of hard-coding the key in committed config:

"headers": { "x-api-key": "${env:FIBER_API_KEY}" }

Option C — via Authorization: Bearer header

Same shape as Option B, but using the standard bearer-token header. Useful if your MCP client only supports Authorization-style auth.

"headers": { "Authorization": "Bearer sk_live_..." }

Resolution order

When 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.

V3 (OAuth)

V3 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.

Example Usage

Once connected, you can ask your AI agent:

• “Search for SaaS companies in New York with 50-200 employees”

• “Find the CEO of Stripe and get their work email”

• “How many credits do I have left?”

• “Enrich this LinkedIn profile: linkedin.com/in/...”

The agent will use the MCP tools to execute these requests directly.

FAQ

Connection not working? Ensure 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.

Getting authentication errors? Make 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 above. Get a key at fiber.ai/app/api.

Should I put the key in chat or in headers? For 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.

Which server should I use? Start with V2 if you have an API key and want the curated common operations. Use V3 if you want every public operation and prefer SSO over a pasted key. Use Core if you prefer a tiny tool surface (5 meta-tools) and want the agent to discover endpoints at runtime — same API-key auth as V2. You can register more than one at the same time — many users register V2 plus Core for maximum flexibility.

Can I use more than one server at the same time? Yes. The server names (fiber-ai-v2, fiber-ai-v3, fiber-ai-core) stay distinct, so you can register all three with no conflict.