TokenLab MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 581 installs a week from npm. Last commit 16 Sep 2026.
TokenLab MCP server: 31 default and 80 full-profile tools for models, media, tasks, and files.
Today is the operative word: we check TokenLab MCP Server every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add tokenlab -- npx -y @tokenlabai/mcp-server
{
"mcpServers": {
"tokenlab": {
"args": [
"-y",
"@tokenlabai/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.tokenlab]
command = "npx"
args = ["-y", "@tokenlabai/mcp-server"]
{
"mcpServers": {
"tokenlab": {
"args": [
"-y",
"@tokenlabai/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"tokenlab": {
"args": [
"-y",
"@tokenlabai/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
TOKENLAB_API_BASE (Optional TokenLab API base URL. Defaults to https://api.tokenlab.sh.), TOKENLAB_API_KEY (Optional TokenLab API key. Required for LLM inference, multimodal generation, async task, embedding, rerank, and translation tools.), TOKENLAB_REQUEST_TIMEOUT_MS (Optional request timeout in milliseconds. Defaults to 120000.), TOKENLAB_MCP_TOOL_PROFILE (Optional generated tool profile: catalog, core (default), or full.), TOKENLAB_MCP_SCHEMA_MODE (Optional tool schema mode: portable, exact, or strict. Defaults to the selected profile's tested mode.), TOKENLAB_MCP_MAX_FILE_BYTES (Optional maximum local upload size per file. Defaults to 104857600 bytes.), TOKENLAB_MCP_INLINE_BYTES (Optional maximum response size returned inline. Defaults to 2097152 bytes.), TOKENLAB_ARTIFACT_DIR (Optional local directory for response artifacts that are not returned inline.).
The author declared them in the registry entry; get the values from the project itself.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Model Context Protocol server for Studex tools, notifications, and profile integrations
MCP server for Planfix API — tasks, contacts. 3 tools.
Delora MCP server for cross-chain quotes, supported chains, tokens, and tools.
MCP server for editing STL 3D model files
TrackingTime MCP server for profile, events, users, projects, tasks, customers, and services.
Hosted MCP server for LinkedIn: 31 tools for profiles, search, messaging, posts, enrichment.
MCP server for PLANKA kanban boards. Full CRUD for cards, tasks, comments, and labels.
Answers built from our own checks of this server.