Koskamo

Fiber AI MCP

An agent-native B2B data platform that allows LLM agents to search companies, enrich contacts, reveal work contact details like emails and phones, and run bulk audience workflows for sales, recruiting, and GTM operations.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Fiber AI MCP logo, by Fiber AIVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Fiber AI
MCP endpoint (Streamable HTTP)
https://mcp.fiber.ai/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Can change data (1)

5 of 5 have a description · 5 of 5 declare behavior hints · 0 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to fiber.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search companies and discover people with filters or natural language
  • Enrich profiles with 44+ fields including experiences, education, and skills
  • Reveal work contact details like emails and phones from known LinkedIn URLs
  • Run bulk audience workflows to build, estimate, enrich, and export lists

Source and maintenance

Vendor evidenceRegistry 1.0.0
Maintenance checked

Protocol and capabilities

Server
fiber-core 3.2.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
3 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "logging": {},
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "subscribe": false,
    "listChanged": true
  },
  "extensions": {
    "io.modelcontextprotocol/ui": {}
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Fiber AI API - Discovery and execution tools. HOW TO USE (3 steps): 1. search_endpoints("your intent", constraints=[...], preferredTags=[...], tagPack="...") - Choose the best operations with ranked alternatives 2. get_endpoint_details_full("operationId") - Get complete schema and examples for complex fields 3. call_operation("operationId", {body: {...}}) - Execute EXAMPLES: - "find companies" → search_endpoints("find AI companies in SF", constraints=["country", "headcount"]) → companySearch - "get email" → search_endpoints("reveal work email for known profile") → syncContactEnrichment - "find people" → search_endpoints("find VP engineering in fintech") → peopleSearch AUTHENTICATION: Every API call requires an apiKey parameter. Ask the user for their Fiber API key (starts with sk_live_ or sk_test_) and include it in every call_operation request body. FOR COMPLEX WORKFLOWS (bulk operations, audiences): Read llms://fiber.ai/llms.txt for step-by-step guidance. For API choice among similar operations, read llms://fiber.ai/api-selector.

Tools

5 advertised

search_endpoints — Search Endpoints
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Canonical API selection tool for endpoint discovery and ranking. Use this first to get the top recommended operations for a user intent. Supports optional constraints plus tag-scoped selection via preferredTags, excludedTags, or a curated tagPack key.

search_endpoints input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "query": {
      "type": "string"
    },
    "tagPack": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "constraints": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "excludedTags": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "preferredTags": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
search_endpoints output schema
{
  "type": "object",
  "additionalProperties": true
}
search_endpoints annotations
{
  "title": "Search Endpoints",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true
}
list_tag_packs — List Tag Packs
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

List curated tag packs for large tool catalogs. Use this to narrow exploration (for example social-media or enrichment).

list_tag_packs input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_tag_packs output schema
{
  "type": "object",
  "additionalProperties": true
}
list_tag_packs annotations
{
  "title": "List Tag Packs",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true
}
list_all_endpoints — List All Endpoints
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

List available Fiber API endpoints with optional tag/search filtering.

list_all_endpoints input schema
{
  "type": "object",
  "properties": {
    "tags": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "limit": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "search": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "tagPack": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    }
  },
  "additionalProperties": false
}
list_all_endpoints output schema
{
  "type": "object",
  "additionalProperties": true
}
list_all_endpoints annotations
{
  "title": "List All Endpoints",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true
}
get_endpoint_details_full — Get Endpoint Details
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get COMPLETE schema and details for a specific API operation. Use this BEFORE calling an API to understand exactly what parameters are needed. Args: operationId: The operation ID (e.g., "syncContactEnrichment") Returns: Complete schema including all required/optional fields, request body schema, response schema, and example usage.

get_endpoint_details_full input schema
{
  "type": "object",
  "required": [
    "operationId"
  ],
  "properties": {
    "operationId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
get_endpoint_details_full output schema
{
  "type": "object",
  "additionalProperties": true
}
get_endpoint_details_full annotations
{
  "title": "Get Endpoint Details",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true
}
call_operation — Call Operation
Advertised by the server during the last successful anonymous check.
Open-world

Execute any Fiber API operation by operationId. IMPORTANT: - Most operations require `apiKey` in the request body. - Prefer search_endpoints() first when operation choice is ambiguous. - Use get_endpoint_details_full(operationId='...') first for complex/nested parameter shapes. Args: operationId: The operation ID to call params: Parameters dict: {"body": {...}, "path": {...}, "query": {...}} Returns: API response data or error details.

call_operation input schema
{
  "type": "object",
  "required": [
    "operationId"
  ],
  "properties": {
    "params": {
      "anyOf": [
        {
          "type": "object",
          "additionalProperties": true
        },
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null
    },
    "operationId": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
call_operation output schema
{
  "type": "object",
  "additionalProperties": true
}
call_operation annotations
{
  "title": "Call Operation",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Prompts

0 advertised

No prompt definitions available.

Resources

3 advertised

get_llms_txt

Advertised by the server during the last successful anonymous check.

Main LLM guide with workflows, rules, and best practices. Read this FIRST for audience workflows, credit costs, and patterns.

get_llms_txt URI
llms://fiber.ai/llms.txt

MIME type: text/plain

get_audience_workflow_doc

Advertised by the server during the last successful anonymous check.

Complete guide for audience workflows (multi-step process). Read this when user wants to build audiences, run bulk enrichment, or export data.

get_audience_workflow_doc URI
llms://fiber.ai/docs/audience-workflow

MIME type: text/plain

get_api_selector_doc

Advertised by the server during the last successful anonymous check.

Decision guide for selecting the best API among similar operations. Read this when multiple APIs appear relevant (for example kitchen-sink vs search).

get_api_selector_doc URI
llms://fiber.ai/api-selector

MIME type: text/plain

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
554 ms
95th percentile latency
554 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 554 ms · metadata changed · 5 tool(s), 3 resource(s), 0 resource template(s), 0 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http fiber-ai-mcp https://mcp.fiber.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add fiber-ai-mcp --url https://mcp.fiber.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable fiber-ai-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "fiber-ai-mcp": {
      "url": "https://mcp.fiber.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "fiber-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.fiber.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start fiber-ai-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "fiber-ai-mcp": {
      "type": "http",
      "url": "https://mcp.fiber.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http fiber-ai-mcp https://mcp.fiber.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://mcp.fiber.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "fiber-ai-mcp": {
      "serverUrl": "https://mcp.fiber.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Fiber AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run Fiber AI MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing