Otter Bridge MCP Server

@typangaa

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

typangaa

投稿者

Alex Pang

Otter Bridge MCP Server について

OtterBridge is a lightweight, flexible server for connecting applications to various Large Language Model providers. Following the principles of simplicity and composability outlined in Anthropic's guide to building effective agents, OtterBridge provides a clean interface to LLMs

#otterbridge#llm-connector#server

Otter Bridge MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "otterbridge": {
      "command": "uv",
      "args": [
        "run",
        "server.py"
      ]
    }
  }
}

Otter Bridge MCP Server のツール

Send messages to LLMs and get AI-generated responses

Retrieve information about available language models

概要

What is Otter Bridge?

Otter Bridge is a lightweight, flexible MCP server that connects applications to various Large Language Model providers. It provides a clean, composable interface for interacting with LLMs, currently supporting Ollama with planned expansion to ChatGPT and Claude. Designed for developers building agent workflows, it follows Anthropic’s principles of simplicity and composability.

How to use Otter Bridge?

Install prerequisites (Ollama and uv), clone the repository, install dependencies with uv add -r requirements.txt, copy .env.example to .env, and configure environment variables. Start the server manually with uv run server.py or automatically via MCP clients like Claude Desktop (add the server to the desktop configuration). Two tools are available: chat (send messages to LLMs) and list_models (retrieve available model information).

Key features of Otter Bridge

Provider-agnostic design (currently Ollama, ChatGPT and Claude planned)
Simple, composable architecture inspired by effective agent patterns
Lightweight server built with FastMCP
Easy model management and retrieval of model capabilities
Configurable via environment variables (OLLAMA_BASE_URL, DEFAULT_MODEL)

Use cases of Otter Bridge

Integrate a local LLM (Ollama) into any MCP-compatible application
Build custom agent workflows that switch between providers as they become available
Prototype LLM-powered features using a fast, local server before moving to cloud APIs
Seamlessly connect Claude Desktop with Ollama models for on-premise AI assistance

よくある質問

What LLM providers does Otter Bridge support?

Currently, Ollama is supported. Support for ChatGPT is planned for Q2 2025 and Claude for Q3 2025.

What are the prerequisites for running Otter Bridge?

You need Ollama installed and running on the default port, and the `uv` Python package manager installed.

How do I integrate Otter Bridge with Claude Desktop?

Add the following configuration to your Claude Desktop config file (adjust the path to match your local installation): `{"otterbridge": {"command": "uv", "args": ["--directory", "<path-to-otterbridge>", "run", "server.py"]}}`.

What environment variables can I configure?

- `OLLAMA_BASE_URL`: URL of the Ollama server (default: http://localhost:11434) - `DEFAULT_MODEL`: Default model to use (default: llama3.3)

What tools does Otter Bridge expose?

It exposes two tools: `chat` for sending

「開発者ツール」の他のコンテンツ

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

Pugi

Pugi Inc.

Pugi is an AI product team in your chat. Describe a business in a few sentences and Pugi plans, designs, builds and checks a real website, shows a live preview, and puts it live on its own address. Ask for changes in pla

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott