What is the TokenLab MCP Server MCP server?
TokenLab MCP server: 31 default and 80 full-profile tools for models, media, tasks, and files.
How to install TokenLab MCP Server
Copy-paste configuration for popular MCP clients.
TOKENLAB_API_BASEOptional TokenLab API base URL. Defaults to https://api.tokenlab.sh.
TOKENLAB_API_KEYsecretOptional TokenLab API key. Required for LLM inference, multimodal generation, async task, embedding, rerank, and translation tools.
TOKENLAB_REQUEST_TIMEOUT_MSOptional request timeout in milliseconds. Defaults to 120000.
TOKENLAB_MCP_TOOL_PROFILEOptional generated tool profile: catalog, core (default), or full.
TOKENLAB_MCP_SCHEMA_MODEOptional tool schema mode: portable, exact, or strict. Defaults to the selected profile's tested mode.
TOKENLAB_MCP_MAX_FILE_BYTESOptional maximum local upload size per file. Defaults to 104857600 bytes.
TOKENLAB_MCP_INLINE_BYTESOptional maximum response size returned inline. Defaults to 2097152 bytes.
TOKENLAB_ARTIFACT_DIROptional local directory for response artifacts that are not returned inline.
TOKENLAB_MANAGEMENT_TOKENsecretOptional workspace Management Token (mt-...) for webhook tools in the full profile. Separate from inference API keys; never put it in tool arguments.
Related MCP servers

io.github.heidiEC/context-pod
Persistent context for AI agents built fromlearned vectors with certainty scores.

CiteVahti
Checks whether each cited source supports the claim it backs. Blinded human-first, local-first.

Vahtian
Freeze a corpus, check it for drift, keep a hash-chained audit ledger. Local-first, stdlib-only.
This is just a test publish, delete me
Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back.
View repository →
GitHub Repository Intelligence
Repo intel for AI coding agents: overview, PRs, contributors, hot files, CI, deps. Remote MCP.
