TokenLab MCP Server

MCP server for TokenLab model discovery, pricing, native endpoints, and inference helpers.

Remote serverstreamable-http

What is the TokenLab MCP server?

MCP server for TokenLab model discovery, pricing, native endpoints, and inference helpers. That is what the tokenlab mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

OpenAPI-generated Model Context Protocol server for TokenLab public model discovery, pricing, native LLM endpoints, multimodal generation, async tasks, files, embeddings, rerank, translation, resources, prompts, and the broader developer API.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • TOKENLAB_API_BASE — optional, defaults to https://api.tokenlab.sh
  • TOKENLAB_API_KEY — optional; required for text inference, multimodal generation, async task, embedding, rerank, and translation tools
  • TOKENLAB_MCP_TOOL_PROFILE — optional, catalog, core (default), or full
  • TOKENLAB_MCP_SCHEMA_MODE — optional, portable, exact, or strict; defaults to the selected profile's tested mode
  • TOKENLAB_REQUEST_TIMEOUT_MS — optional request timeout in milliseconds, defaults to 120000
  • TOKENLAB_MCP_MAX_FILE_BYTES — optional maximum local upload size per file, defaults to 104857600 (100 MiB)
  • TOKENLAB_MCP_INLINE_BYTES — optional maximum binary/JSON response size returned inline, defaults to 2097152 (2 MiB)
  • TOKENLAB_ARTIFACT_DIR — optional output directory for non-inline response artifacts, defaults to the OS temp directory under tokenlab-mcp
  • package.json.mcpName — io.github.hedging8563/tokenlab
  • Websitehttps://tokenlab.sh/mcp
  • Docshttps://docs.tokenlab.sh
  • OpenAPIhttps://docs.tokenlab.sh/openapi.json

What it needs from you

Configuration is passed through the environment: TOKENLAB_API_BASE, TOKENLAB_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

This sits in the file and storage access group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. TokenLab's toolset — TOKENLAB_API_BASE, TOKENLAB_API_KEY, TOKENLAB_MCP_TOOL_PROFILE and 11 more — is a fair guide to whether it matches your workflow. It is maintained by hedging8563; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch TokenLab.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
TOKENLAB_API_BASEoptional, defaults to https://api.tokenlab.sh
TOKENLAB_API_KEYoptional; required for text inference, multimodal generation, async task, embedding, rerank, and translation tools
TOKENLAB_MCP_TOOL_PROFILEoptional, catalog, core (default), or full
TOKENLAB_MCP_SCHEMA_MODEoptional, portable, exact, or strict; defaults to the selected profile's tested mode
TOKENLAB_REQUEST_TIMEOUT_MSoptional request timeout in milliseconds, defaults to 120000
TOKENLAB_MCP_MAX_FILE_BYTESoptional maximum local upload size per file, defaults to 104857600 (100 MiB)
TOKENLAB_MCP_INLINE_BYTESoptional maximum binary/JSON response size returned inline, defaults to 2097152 (2 MiB)
TOKENLAB_ARTIFACT_DIRoptional output directory for non-inline response artifacts, defaults to the OS temp directory under tokenlab-mcp
package.json.mcpNameio.github.hedging8563/tokenlab
Websitehttps://tokenlab.sh/mcp
Docshttps://docs.tokenlab.sh
OpenAPIhttps://docs.tokenlab.sh/openapi.json
Skillshttps://github.com/hedging8563/tokenlab-skills
ProfileEndpoint tools

How to install the TokenLab MCP server

{
  "mcpServers": {
    "tokenlab": {
      "command": "npx",
      "args": ["-y", "@tokenlabai/mcp-server"],
      "env": {
        "TOKENLAB_API_BASE": "your-value",
        "TOKENLAB_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
TOKENLAB_API_BASECredential the server authenticates with.Yes
TOKENLAB_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use TokenLab to TOKENLAB API BASE.
  • Use TokenLab to TOKENLAB API KEY.
  • Use TokenLab to TOKENLAB MCP TOOL PROFILE.

Frequently asked questions

It connects TokenLab to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (TOKENLAB_API_BASE, TOKENLAB_API_KEY, TOKENLAB_MCP_TOOL_PROFILE, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with TokenLab directly.