Telemem MCP Server

What the code does

We read the source, 19 h ago · rules 3dff92dd89df

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

                state = pickle.load(f)

        self._store_path = os.path.join(self._base_dir or "video_segments", f"simple_mem_store_{self._memory_name}.json")

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

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 telemem -- uvx telemem

{
  "mcpServers": {
    "telemem": {
      "args": [
        "telemem"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.telemem]
command = "uvx"
args = ["telemem"]

{
  "mcpServers": {
    "telemem": {
      "args": [
        "telemem"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "telemem": {
      "args": [
        "telemem"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: OPENAI_API_KEY (API key for the default OpenAI LLM/embedder (not needed with a local TELEMEM_CONFIG)), TELEMEM_CONFIG (Path to a TeleMem YAML/JSON config, e.g. the fully-local Ollama + FAISS setup (config/config.ollama.yaml)), TELEMEM_DEFAULT_USER_ID (Default memory scope when tool calls omit user_id/agent_id/run_id (default: telemem-mcp)). The author declared them in the registry entry; get the values from the project itself.