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 two MCP servers:

Server	URL	Best For
V2	`https://mcp.fiber.ai/mcp/v2/`	~10 curated, high-priority API tools (`api_companySearch`, `api_peopleSearch`, `api_individualRevealSync`, etc.)
Core	`https://mcp.fiber.ai/mcp`	4 meta tools that can discover and call any of 100+ API endpoints (`search_endpoints`, `call_operation`, `list_all_endpoints`, `get_endpoint_details_full`)

Which one should I use? It depends on your workflow. V2 gives your agent ~10 direct tools for the most common operations (search, enrich, reveal) — easiest for most agents. Core gives access to all 100+ API endpoints through meta tools that discover and call any endpoint dynamically. Most users start with V2; power users or those building complex workflows benefit from Core or both.

Setup Instructions

Cursor

Visit the link below to install automatically:

Install Fiber AI V2 in Cursor — Copy the link below, paste it into your browser address bar, and press Enter.


cursor://anysphere.cursor-deeplink/mcp/install?name=Fiber-AI-v2&config=eyJ1cmwiOiJodHRwczovL21jcC5maWJlci5haS9tY3AvdjIvIn0=

Install Fiber AI Core in Cursor — Copy the link below, paste it into your browser address bar, and press Enter.


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

Or manually:

Open Cursor Settings → Features → MCP.
Click "+ Add New MCP Server".
Name: Fiber-AI-v2
Type: HTTP
URL: https://mcp.fiber.ai/mcp/v2/

Claude Code

Run the following in your terminal:


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

To also add the Core server:


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

Once added, 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/.

Alternatively, edit your claude_desktop_config.json:


{
  "mcpServers": {
    "fiber-mcp-v2": {
      "url": "https://mcp.fiber.ai/mcp/v2/",
      "transport": { "type": "http" }
    },
    "fiber-mcp": {
      "url": "https://mcp.fiber.ai/mcp",
      "transport": { "type": "http" }
    }
  }
}

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/"

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/

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

Or add to your .vscode/mcp.json:


{
  "mcpServers": {
    "fiber-ai": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.fiber.ai/mcp/v2/"]
    }
  }
}

Windsurf

Press Ctrl/Cmd + , to open Windsurf settings.
Scroll to Cascade → MCP servers.
Select Add Server → Add custom server.
Add the following:


{
  "mcpServers": {
    "fiber-ai": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.fiber.ai/mcp/v2/"]
    }
  }
}

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/"],
      "env": {}
    }
  }
}

Others

Most MCP-compatible tools can be configured with:

Command: npx
Arguments: -y mcp-remote https://mcp.fiber.ai/mcp/v2/
Environment: None

Available Tools

V2 Server (`/mcp/v2/`)

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

Tool	Description
`api_companySearch`	Search for companies by industry, location, size, funding, etc.
`api_peopleSearch`	Search for people by title, seniority, department, etc.
`api_individualRevealSync`	Reveal work email and phone for a LinkedIn profile
`api_companyLiveFetch`	Get live LinkedIn data for a company
`api_personLiveFetch`	Get live LinkedIn data for a person
`api_getOrgCredits`	Check your credit balance
...	~10 curated tools covering the most common Fiber AI operations

Core Server (`/mcp`)

Meta tools for dynamic endpoint discovery:

Tool	Description
`search_endpoints`	Search for API endpoints by keyword
`list_all_endpoints`	List all available API endpoints
`get_endpoint_details_full`	Get full schema details for an endpoint
`call_operation`	Call any API endpoint by its operation ID

Authentication

All API calls require your Fiber AI API key. Pass it in the request body as apiKey:


"Search for AI companies" → Agent calls api_companySearch with { "apiKey": "sk_live_...", "searchParams": { ... } }

Get your API key from fiber.ai/app/api.

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 passing a valid apiKey in your requests. Get one at fiber.ai/app/api.

Which server should I use? Use V2 for most use cases — it provides direct tools for the most common API operations. Use Core if you need access to all 100+ API endpoints or prefer a discovery-based approach.

Can I use both servers at the same time? Yes. Many users add both for maximum flexibility.