What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
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.
{
"mcpServers": {
"tokenlab": {
"command": "npx",
"args": [
"-y",
"@tokenlabai/mcp-server"
],
"env": {
"TOKENLAB_API_BASE": "<YOUR_TOKENLAB_API_BASE>",
"TOKENLAB_API_KEY": "<YOUR_TOKENLAB_API_KEY>",
"TOKENLAB_REQUEST_TIMEOUT_MS": "<YOUR_TOKENLAB_REQUEST_TIMEOUT_MS>",
"TOKENLAB_MCP_TOOL_PROFILE": "<YOUR_TOKENLAB_MCP_TOOL_PROFILE>",
"TOKENLAB_MCP_SCHEMA_MODE": "<YOUR_TOKENLAB_MCP_SCHEMA_MODE>",
"TOKENLAB_MCP_MAX_FILE_BYTES": "<YOUR_TOKENLAB_MCP_MAX_FILE_BYTES>",
"TOKENLAB_MCP_INLINE_BYTES": "<YOUR_TOKENLAB_MCP_INLINE_BYTES>",
"TOKENLAB_ARTIFACT_DIR": "<YOUR_TOKENLAB_ARTIFACT_DIR>",
"TOKENLAB_MANAGEMENT_TOKEN": "<YOUR_TOKENLAB_MANAGEMENT_TOKEN>"
}
}
}
}Related MCP servers

io.github.heidiEC/context-pod
Persistent context for AI agents built fromlearned vectors with certainty scores.
Behavioral memory layer that learns your preferences and context across Claude, Cursor, and Codex.

TokRepo — AI Asset Registry
TokRepo MCP: tokrepo_discover, tokrepo_verify, tokrepo_install_plan for reusable AI assets.

Bee governed intelligence for chat, code, research, documents, and memory.

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.
