home / mcp / agent farm mcp server
Runs tool-enabled agents for parallel tasks, chunked writes, and multi-perspective analysis in an MCP environment.
Configuration
View docs{
"mcpServers": {
"bossx429-agent-farm": {
"command": "/home/kyle/repos/agent-farm/.venv/bin/python",
"args": [
"-m",
"agent_farm.server"
]
}
}
}Agent Farm MCP Server enables you to run tool-enabled agents that collaborate to perform complex tasks. It orchestrates multiple specialized roles, supports parallel work patterns, and can generate large documents or code by chunking work across workers. This guide walks you through practical usage, installation steps, and important configuration notes so you can start using the server effectively.
You operate Agent Farm through an MCP client that talks to the server to deploy swarms, run tool-enabled agents, and collect results. Start a swarm to assign tasks to colonies, monitor colony health, and trigger specialized swarms for file operations, code generation, or multi-perspective analysis. Use chunked workflows when you need large outputs like long documents or multi-function code files. The system automatically handles parallel work and assembles the final result.
Prerequisites: ensure you have Python installed and access to a shell. You will also use a virtual environment tool to isolate dependencies.
1) Prepare your project directory and environment.
2) Create and activate a virtual environment using the project’s tooling.
3) Install the server in editable mode to develop and run locally.
4) Run the server module to start listening for MCP client connections.
Agent Farm provides a standard runtime path to start the server locally from a virtual environment. The recommended runtime command is to execute the module that contains the server entry point within your virtual environment, for example: activate your virtual environment and run python -m agent_farm.server.
Create a new bug colony with configurable types (standard, fast, heavy, hybrid) to run a set of tasks.
List all active colonies with current health and task status.
Provide detailed status for a specific colony including health, active tasks, and progress.
Run a quick health check on a colony to verify it is responsive.
Remove a colony and clean up its resources.
Remove colonies that have been idle beyond a configured threshold.
Return comprehensive statistics about the MCP environment and swarm activity.
Publish a set of tasks to a colony for execution.
Spawn a one-shot swarm and deploy it immediately.
A 4-perspective review workflow for code, focusing on structure, patterns, quality, and performance.
Generate code along with tests and documentation based on a spec.
Perform parallel file operations such as read, write, copy, or delete across multiple paths.
Execute parallel shell commands across multiple agents.
Send parallel HTTP requests to target endpoints and aggregate results.
Run multi-angle knowledge queries to gather diverse perspectives.
Deploy bugs equipped with real system tools to perform tasks.
Quickly check the health of the host system and key services.
Perform reconnaissance on directories or codebases to map structure and content.
Deep disk/file analysis to extract actionable insights.
Operate a single worker with access to full tooling for focused tasks.
Direct file write that bypasses large-language-model output limits to create large content.
Standalone synthesis of any JSON results to produce a final consolidated view.