Schema | TokenLab MCP Server

TokenLab MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`TOKENLAB_API_KEY`	No	Optional API key required for inference helper tools
`TOKENLAB_API_BASE`	No	Optional base URL for the TokenLab API	https://api.tokenlab.sh

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
list_modelsB	List public TokenLab models, optionally filtered by recommended task.
get_modelA	Fetch public TokenLab model details for one model ID.
get_model_pricingA	Fetch public TokenLab pricing details for one model ID.
compare_modelsA	Compare public TokenLab model details and pricing for several model IDs.
create_chat_completionB	Create a non-streaming TokenLab OpenAI-compatible Chat Completions call. Requires TOKENLAB_API_KEY.
create_responseA	Create a non-streaming TokenLab Responses API call with text or native structured input. Requires TOKENLAB_API_KEY.
create_anthropic_messageA	Create a non-streaming TokenLab Anthropic Messages call with native messages, multimodal blocks, and tools. A prompt shortcut remains available for simple calls. Requires TOKENLAB_API_KEY.
create_gemini_contentB	Create a TokenLab Gemini generateContent call with native contents, multimodal parts, generation config, and tools. A prompt shortcut remains available for simple calls. Requires TOKENLAB_API_KEY.
get_api_overviewA	Fetch TokenLab's agent-readable API overview.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hedging8563/tokenlab-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server