protogrid

Search / io.github.hedging8563/tokenlab

TokenLab MCP Server

R0· no sign-in

TokenLab MCP server: 32 default and 89 full-profile tools for models, media, tasks, and files.

v0.6.31 · active · repository · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality81good
Trust97of 100
Uptime, 30 days100%
Latency p50965 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "tokenlab": {
      "type": "http",
      "url": "https://mcp.tokenlab.sh/mcp"
    }
  }
}
claude mcp add --transport http tokenlab https://mcp.tokenlab.sh/mcp
[mcp_servers.tokenlab]
url = "https://mcp.tokenlab.sh/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tokenlab": {
      "type": "remote",
      "url": "https://mcp.tokenlab.sh/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "tokenlab": {
      "type": "http",
      "url": "https://mcp.tokenlab.sh/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=tokenlab&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLnRva2VubGFiLnNoL21jcCJ9"
}
{
  "servers": {
    "tokenlab": {
      "type": "http",
      "url": "https://mcp.tokenlab.sh/mcp"
    }
  }
}
{
  "mcpServers": {
    "tokenlab": {
      "httpUrl": "https://mcp.tokenlab.sh/mcp"
    }
  }
}
extensions:
  "tokenlab":
    enabled: true
    name: "tokenlab"
    type: streamable_http
    uri: "https://mcp.tokenlab.sh/mcp"
    timeout: 300

Quality 81 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations3 of 3 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: open_tokenlab_model_explorer (idempotentHint); generate_tokenlab_endpoint_example (idempotentHint); compare_tokenlab_models (idempotentHint)
  • pass
    tools.token_costabout 476 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 1 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know @tokenlabai/[email protected]

3 tools, about 476 tokens to load them all · tool set 921bf83741b4 · checked 2026-10-20 06:17 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 97 / 100

provenance90
liveness100
freshness100
hygiene100

+repository +namespace-matches-repo +website +reachable +uptime-100% +updated-1d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

@tokenlabai/[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.tokenlab.sh/mcp streamable-httpnoneyes100%965 ms2025-11-252026-10-20
packageregistryversionruntimesecrets
@tokenlabai/mcp-servernpm0.6.31–TOKENLAB_API_KEY, TOKENLAB_MANAGEMENT_TOKEN

Tools (3)

compare_tokenlab_modelsread-onlyCompare platform price, context window and capabilities for specific TokenLab model IDs, from the live public catalog.
generate_tokenlab_endpoint_exampleread-onlyGenerate a copyable cURL example for OpenAI-compatible or native TokenLab endpoints.
open_tokenlab_model_explorerread-onlyBrowse TokenLab models by category or search query, with context window, capabilities and platform price from the live public catalog.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.hedging8563/tokenlab",
  "title": "TokenLab MCP Server",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.tokenlab.sh/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.6.31",
  "packages": [
    {
      "version": "0.6.31",
      "transport": {
        "type": "stdio"
      },
      "identifier": "@tokenlabai/mcp-server",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "TOKENLAB_API_BASE",
          "format": "string",
          "description": "Optional TokenLab API base URL. Defaults to https://api.tokenlab.sh."
        },
        {
          "name": "TOKENLAB_API_KEY",
          "format": "string",
          "isSecret": true,
          "description": "Optional TokenLab API key. Required for LLM inference, multimodal generation, async task, embedding, rerank, and translation tools."
        },
        {
          "name": "TOKENLAB_REQUEST_TIMEOUT_MS",
          "format": "number",
          "description": "Optional request timeout in milliseconds. Defaults to 120000."
        },
        {
          "name": "TOKENLAB_MCP_TOOL_PROFILE",
          "format": "string",
          "description": "Optional generated tool profile: catalog, core (default), or full."
        },
        {
          "name": "TOKENLAB_MCP_SCHEMA_MODE",
          "format": "string",
          "description": "Optional tool schema mode: portable, exact, or strict. Defaults to the selected profile's tested mode."
        },
        {
          "name": "TOKENLAB_MCP_MAX_FILE_BYTES",
          "format": "number",
          "description": "Optional maximum local upload size per file. Defaults to 104857600 bytes."
        },
        {
          "name": "TOKENLAB_MCP_INLINE_BYTES",
          "format": "number",
          "description": "Optional maximum response size returned inline. Defaults to 2097152 bytes."
        },
        {
          "name": "TOKENLAB_ARTIFACT_DIR",
          "format": "string",
          "description": "Optional local directory for response artifacts that are not returned inline."
        },
        {
          "name": "TOKENLAB_MANAGEMENT_TOKEN",
          "format": "string",
          "isSecret": true,
          "description": "Optional workspace Management Token (mt-...) for webhook tools in the full profile. Separate from inference API keys; never put it in tool arguments."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/hedging8563/tokenlab-mcp-server",
    "source": "github"
  },
  "websiteUrl": "https://tokenlab.sh/mcp",
  "description": "TokenLab MCP server: 32 default and 89 full-profile tools for models, media, tasks, and files."
}