MCP Agent Server

@LeadBroaf

About MCP Agent Server

Open-source, modular “brain” for AI employees. Integrates with n8n and workflow engines, features persistent agent memory, natural language interface, and feedback loops. SaaS-ready, extensible, and easy to deploy with Docker.

#mcp-agent-server #ai-employees #workflow-automation

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-agent-server": {
      "type": "http",
      "url": "http://localhost:4000"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Agent Server?

MCP Agent Server is an open‑source, modular “brain” for AI employees/agents, designed to work seamlessly with n8n and other workflow engines. It enables users to create persistent agents with memory, feedback loops, and natural language interfaces.

How to use MCP Agent Server?

Clone the repository, copy any docs and memory folders, then build and run with docker-compose up --build. The server becomes available at http://localhost:4000. You need Node.js and Docker installed. After startup, register a user via POST /users/register, obtain an API key, and use that key to manage agents and memory endpoints.

Key features of MCP Agent Server

Open‑source modular “brain” for AI employees
Persistent, agent‑centric memory and feedback loops
Natural language instruction parsing and task orchestration
Easy deployment with Docker Compose
Opinionated design inspired by the “AI employee” metaphor
API‑based user and API key management

Use cases of MCP Agent Server

Building AI employees that learn from feedback and improve over time
Creating vertical solutions like “AI Analyst” or “AI Admin” with prebuilt skills
Integrating persistent agents into n8n workflows for automated task execution
Offering simple, non‑technical AI agent experiences for SMBs and individuals

FAQ from MCP Agent Server

How are agents authenticated?

All endpoints except /health, /users/register, and /users/login require an x-api-key header. API keys are managed per user through dedicated endpoints.

How do I manage users and API keys?

Use POST /users/register to create a user, POST /users/login to get an API key, and GET /users/me/api-keys, POST /users/me/api-keys, DELETE /users/me/api-keys/:id to list, create, or revoke keys.

What are the system requirements?

Node.js and Docker must be installed. The server runs via Docker Compose and listens on port 4000 by default.

How does agent memory work?

Memory and feedback are persistent and agent‑centric. Use POST /agents/:id/memory to add memory/feedback and GET /agents/:id/memory to retrieve it.

Is the MCP Agent Server open source?

Yes, the project is open source and available on GitHub.

Frequently asked questions

How are agents authenticated?

All endpoints except `/health`, `/users/register`, and `/users/login` require an `x-api-key` header. API keys are managed per user through dedicated endpoints.

How do I manage users and API keys?

Use `POST /users/register` to create a user, `POST /users/login` to get an API key, and `GET /users/me/api-keys`, `POST /users/me/api-keys`, `DELETE /users/me/api-keys/:id` to list, create, or revoke keys.

What are the system requirements?

Node.js and Docker must be installed. The server runs via Docker Compose and listens on port 4000 by default.

How does agent memory work?

Memory and feedback are persistent and agent‑centric. Use `POST /agents/:id/memory` to add memory/feedback and `GET /agents/:id/memory` to retrieve it.

Is the MCP Agent Server open source?

Yes, the project is open source and available on GitHub.

Comments

Basic information

More AI & Agents MCP servers

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

MCP Claude Code

SDGLBL

MCP implementation of Claude Code capabilities and more

302

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733

MCP-LLM Bridge

patruff

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

976