Skip to content
MCP server

FreeToken — LLM API discovery

Read-only catalog of LLM APIs with access conditions, dated prices and keyless configs

Install
Pricing
Free
Platforms
API
Runs
Remotely
Version
1.0.0
Listing updated
1 day ago

About FreeToken — LLM API discovery

FreeToken — LLM API discovery is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.

Rather than calling models itself, this service answers questions about them from a public catalog. You can filter cataloged models by provider, protocol, whether a payment card is required and recorded context size, then read the official application links and eligibility conditions for a provider.

Price questions go through dated reference records: one tool lists the price references and their billing scenarios, and another turns input and output token volumes into an estimate for a single scenario. Route status comes from stored, sampled observations rather than live checks, and the guide notes this is not provider-wide uptime. Records older than 30 days are flagged.

No API key or account is needed, and the service says it does not call model providers, access a vault or send email. Requests are capped at 8 KiB, search returns at most 20 records, and anonymous traffic is limited to roughly 60 requests per minute. Guide text covers English, Chinese, Japanese, Spanish and Korean.

Install

Run in a terminal

claude mcp add --transport http catalog https://freetoken.link/mcp

Add to Settings → Connectors → Add custom connector

https://freetoken.link/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "catalog": {
      "url": "https://freetoken.link/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "catalog": {
      "type": "http",
      "url": "https://freetoken.link/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "catalog": {
      "serverUrl": "https://freetoken.link/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "catalog": {
      "type": "http",
      "url": "https://freetoken.link/mcp"
    }
  }
}

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

search_models
Filter models by provider, protocol, card requirement and recorded context size.
get_provider_guide
Read official application links, eligibility conditions and existing steps.
list_price_references
Discover price reference IDs and their billing scenarios before estimating.
estimate_cost
Estimate one dated price scenario from input and output token volumes.
get_route_status
Read the latest stored route observations without running new checks.
export_keyless_config
Generate route-pack, LiteLLM or environment templates for up to five routes.

What it does

Model search
Filter cataloged models by provider, protocol, card requirement and context size.
Provider guides
Read official application links, eligibility conditions and existing steps.
Dated cost estimates
Estimate one price scenario from input and output token volumes.
Route status
Read the latest stored observations from sampled checks without running new ones.
Keyless config export
Generate route-pack, LiteLLM or environment templates for up to five routes.
Staleness flags
Records older than 30 days are marked so you can see how fresh the evidence is.

Good for

  • Find OpenAI-compatible models that need no payment card and offer a large context window
  • Check a provider's application conditions before signing up
  • Estimate the cost of a token workload against dated published prices
  • Generate a LiteLLM or environment config that references keys by variable name

Pricing

Free

No key or account needed; pricing of the service itself not published

Prices change. Check freetoken.link before you buy.

FreeToken — LLM API discovery FAQ

Do I need an API key to use it?

No. Authentication is not required, and the guide asks you not to send keys, passwords or private data.

Why does opening the endpoint in a browser fail?

The endpoint accepts only POST requests from MCP clients, so a browser address bar returns HTTP 405 by design.

What are the request limits?

Requests are limited to 8 KiB, search returns at most 20 records, and anonymous traffic is limited to about 60 requests per minute per IP and Cloudflare location.

Does the status data show real uptime?

No. Status reflects sampled checks, not provider-wide uptime.

Is FreeToken — LLM API discovery free?

Yes. FreeToken — LLM API discovery is free to use.

How do I add FreeToken — LLM API discovery to Claude Code?

Run this command in your terminal: claude mcp add --transport http catalog https://freetoken.link/mcp

What are the best alternatives to FreeToken — LLM API discovery?

The closest alternatives to FreeToken — LLM API discovery are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.

Alternatives to FreeToken — LLM API discovery

  1. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  2. signafAIde

    MCP server

    Local MCP server to set up, verify and check coverage of signed agent action records

    Runs locally
    • 5 tools
    • Freemium
    • Security
  3. Toolkien

    MCP server

    One MCP gateway for all your MCP servers, with code mode, permissions and audit

    Not checked yet
    • 3 tools
    • Remote
    • Open source
    • AI models and LLM tooling
  4. Lugh

    MCP server

    Write, check and dry-run Lugh agent programs with policy, budgets and approvals

    Runs locally
    • 5 tools
    • Open source
    • AI models and LLM tooling
  5. HypePaper

    MCP server

    Research papers, benchmarks, citations and topic experts for AI assistants

    • 58 tools
    • Remote
    • Freemium
    • AI models and LLM tooling