Agent Tasker Mcp

Name: Agent Tasker Mcp
Author: S3bRR

by S3bRRcommunityv1.0.1

Small stdio-only MCP server for running multiple local tasks and returning structured results. It supports single-task execution and concurrent batch execution with explicit task dependencies.

From the registry: Minimal stdio MCP server for parallel task execution by AI agents.

GitHub Repository

Install & configure

Prerequisites

required
Install Python 3.10+
Python 3.10 or newer is required to run the server.
required
Install uvx
Recommended launcher for running the server directly from GitHub without cloning the repository.

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `agent-tasker-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Python 3.10 or newer is required to run the server.
- **Install uvx** — Recommended launcher for running the server directly from GitHub without cloning the repository.

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","git+https://github.com/S3bRR/agent-tasker-mcp.git","agent-tasker-mcp-server","--workers","8"]
- optional environment variables:
  - `AGENT_TASKER_MAX_TASKS`: Maximum number of tasks allowed per execute_batch call. (example: `<max-tasks>`)
  - `AGENT_TASKER_MAX_PAYLOAD_BYTES`: Maximum payload size allowed per task. (example: `<max-payload-bytes>`)
  - `AGENT_TASKER_MAX_MEMORY_MB`: Soft process memory guard in megabytes. (example: `<max-memory-mb>`)

Note: Preferred install path is the recommended uvx command that runs directly from the GitHub repository. The server is stdio-only and also accepts a --workers <n> runtime argument; the README examples use 8.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Preferred install path is the recommended uvx command that runs directly from the GitHub repository. The server is stdio-only and also accepts a --workers <n> runtime argument; the README examples use 8.