Tendem

Provides Tendem API access and task routing for AI agents through MCP clients using a Tendem API key.

typescript

4

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "toloka-tendem-mcp": {
      "command": "uvx",
      "args": [
        "tendem-mcp"
      ],
      "env": {
        "TENDEM_API_KEY": "<your-api-key>"
      }
    }
  }
}

You can run Tendem’s MCP server to connect your AI agents with Tendem’s task platform, enabling automated task execution through your preferred MCP client. This server accepts your Tendem API key and exposes a lightweight interface for agents to request actions and receive results.

How to use

Use the Tendem MCP server with your MCP client to route tasks to Tendem. You will provide your API key to authorize requests, then start the MCP server from your client’s integration flow. Your agent can issue tasks, and Tendem will process them through the configured MCP interface.

How to install

Prerequisites: you need a Tendem account and an API key. You will also use an MCP client integration that supports stdio MCPs (for example uvx) to launch the Tendem MCP server.

Step 1: Obtain your API key. Log into your Tendem account and visit the API tokens page to generate or view your token.

Step 2: Add the Tendem MCP server configuration to your MCP client. Use one of the following examples depending on your client.

claude mcp add tendem -e TENDEM_API_KEY=<your-api-key> -- uvx tendem-mcp

Additional configuration details

Configure the Tendem MCP server with a single stdio entry that uses the uvx launcher and the tendem-mcp subcommand. You must provide the TENDEM_API_KEY environment variable in each configuration.

{
  "mcpServers": {
    "tendem": {
      "type": "stdio",
      "command": "uvx",
      "args": ["tendem-mcp"],
      "env": {
        "TENDEM_API_KEY": "<your-api-key>"
      }
    }
  }
}

Notes on client configuration variants

If you are using Claude Desktop, you add the following to your claude_desktop_config.json to register the Tendem MCP server.

{
  "mcpServers": {
    "tendem": {
      "command": "uvx",
      "args": ["tendem-mcp"],
      "env": {
        "TENDEM_API_KEY": "<your-api-key>"
      }
    }
  }
}

Alternative client examples

OpenAI Codex users can add Tendem in a similar fashion by including the environment key in the command line.

codex mcp add tendem --env TENDEM_API_KEY=<your-api-key> -- uvx tendem-mcp

OpenCode configuration example

OpenCode users can register Tendem MCP with a local mcp configuration.

{
  "mcp": {
    "tendem": {
      "type": "local",
      "command": ["uvx", "tendem-mcp"],
      "environment": {
        "TENDEM_API_KEY": "<your-api-key>"
      }
    }
  }
}