Fim One

v1.0.0Coding Agentsstable

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

aiai-agentai-agentsconnectordag
Share:
1,086
Stars
0
Downloads
0
Weekly
0/5

What is Fim One?

Fim One is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source agent platform for global × china enterprises — wire every system through one agent core. self-hosted, any llm.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Open-source agent platform for Global × China enterprises —

Use Cases

Enterprise system integration through agent core
Self-hosted LLM orchestration with DAG workflows
fim-ai

Maintainer

LicenseNOASSERTION
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx fim-one

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Fim One

FIM One is an open-source, self-hosted agent platform designed for Global and China enterprises that need to wire diverse backend systems through a single AI agent core. Built on FastAPI and Next.js, it supports any OpenAI-compatible LLM provider via LiteLLM (including OpenAI, DeepSeek, Anthropic, and Ollama) and provides RAG pipelines, code execution sandboxes, multi-database connectors, and MCP server integration. Teams adopt FIM One to deploy private, cost-controlled AI agents that work across Chinese enterprise databases (DM, KingbaseES) alongside standard PostgreSQL and MySQL stacks.

Prerequisites

  • Docker and Docker Compose (recommended) or Python 3.11+ with uv and Node.js 18+ for local development
  • An API key for at least one OpenAI-compatible LLM provider (OpenAI, DeepSeek, Anthropic, or a local Ollama instance)
  • Optional: Jina API key for web tools and RAG embedding
  • Git to clone the repository
  • An MCP-compatible client if connecting via the MCP protocol
1

Clone the repository and configure environment

Clone the FIM One repo and copy the example environment file. Edit .env with your LLM provider credentials and optional settings.

git clone https://github.com/fim-ai/fim-one.git
cd fim-one
cp example.env .env
2

Set required environment variables

Edit .env and set at minimum LLM_API_KEY and LLM_MODEL. Optionally set LLM_BASE_URL for non-OpenAI providers, JINA_API_KEY for web tools and RAG, and CODE_EXEC_BACKEND=docker for sandboxed code execution.

LLM_API_KEY=sk-your-key-here
LLM_MODEL=gpt-4o
LLM_BASE_URL=https://api.openai.com/v1
JINA_API_KEY=your-jina-key
CODE_EXEC_BACKEND=docker
3

Start with Docker Compose

Build and start all services using Docker Compose. The platform will be accessible on localhost once containers are running.

docker compose up --build -d
4

Connect MCP servers

FIM One supports connecting external MCP servers in three ways: import an OpenAPI spec, use the AI chat builder, or connect via MCP server URL. Access this through the platform's agent configuration interface.

5

Configure agent workflows with DAG pipelines

Use the React Flow-based visual interface to define DAG-based multi-agent workflows, chaining tools such as document conversion, database queries, code execution, and RAG retrieval into automated pipelines.

Fim One Examples

Client configuration

Add FIM One as an MCP server in your Claude Desktop configuration after starting the platform locally.

{
  "mcpServers": {
    "fim-one": {
      "command": "npx",
      "args": ["fim-one"],
      "env": {
        "LLM_API_KEY": "sk-your-key-here",
        "LLM_MODEL": "gpt-4o"
      }
    }
  }
}

Prompts to try

Use these prompts to explore FIM One's document processing, RAG, and database connectivity capabilities.

- "Convert this PDF to markdown and extract all tables"
- "Query the PostgreSQL database for sales data from last quarter and summarize trends"
- "Execute this Python script in the sandbox and return the output"
- "Search the knowledge base for documents about our Q3 roadmap"
- "Connect to the MySQL database at host:3306 and list all table names"

Troubleshooting Fim One

Docker containers fail to start with networking errors

Ensure Docker Desktop is running and ports are not already in use. Run `docker compose logs` to identify the failing service. For Apple Silicon Macs, confirm Docker is using the correct platform (linux/amd64 emulation or arm64-native images).

LLM API calls return authentication errors

Verify that LLM_API_KEY is correctly set in your .env file with no trailing whitespace. For non-OpenAI providers, also set LLM_BASE_URL to the correct endpoint. Run `docker compose restart` after editing .env to pick up new values.

RAG retrieval returns no results

RAG requires a valid JINA_API_KEY for embedding generation. Confirm the key is set and that documents have been ingested through the platform's document import interface before querying the knowledge base.

Frequently Asked Questions about Fim One

What is Fim One?

Fim One is a Model Context Protocol (MCP) server that open-source agent platform for global × china enterprises — wire every system through one agent core. self-hosted, any llm. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Fim One?

Follow the installation instructions on the Fim One GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Fim One?

Fim One works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Fim One free to use?

Yes, Fim One is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "fim-one": { "command": "npx", "args": ["-y", "fim-one"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Fim One?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides