MCP.so
Sign In

Anthropic Model Context Protocol (MCP) Server with Ollama Integr…

@jorgesandoval

Repository

About Anthropic Model Context Protocol (MCP) Server with Ollama Integr…

Model Context Protocol (MCP) server integrated with an external inference service (e.g., Ollama/Gemma3) via middleware.

#mcp#ollama#ai-inference

Config

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

{
  "mcpServers": {
    "simple-mcp-server-jorgesandoval": {
      "command": "python",
      "args": [
        "test_system.py"
      ]
    }
  }
}

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 Anthropic Model Context Protocol (MCP) Server with Ollama Integration?

A hybrid architecture that combines an Anthropic-compatible Model Context Protocol (MCP) server with Ollama (Gemma3:4b) for local inference. It provides a middleware layer to store conversation context in a SQLite database and exposes standard MCP endpoints for tools, resources, and prompts. Designed for developers who want to run open-source models with any MCP client (e.g., Claude Desktop, VS Code extensions).

How to use Anthropic Model Context Protocol (MCP) Server with Ollama Integration?

Install via the provided setup.sh script or manually with Docker and Ollama. After starting the containers, interact via curl POST requests to the middleware at http://localhost:8080/infer with a JSON body containing session_id and content. Alternatively, connect any MCP client directly to the MCP server on port 3000.

Key features of Anthropic Model Context Protocol (MCP) Server with Ollama Integration

  • Fully implements the official MCP protocol (JSON‑RPC 2.0, initialization, version negotiation)
  • Supports tools, resources, and prompt templates as per the MCP specification
  • Uses SQLite for persistent conversation context storage
  • Middleware bridges MCP server and Ollama/Gemma3:4b for inference
  • Containerized with Docker for easy deployment
  • Health check endpoint (GET /health) for monitoring

Use cases of Anthropic Model Context Protocol (MCP) Server with Ollama Integration

  • Building context-aware conversational agents using open-source models locally
  • Integrating a local LLM backend into MCP-compatible tools (Claude Desktop, Cursor, etc.)
  • Experimenting with the MCP protocol without relying on Anthropic’s cloud services
  • Developing and testing MCP-based applications with full control over data storage

FAQ from Anthropic Model Context Protocol (MCP) Server with Ollama Integration

What are the runtime requirements?

Python 3.10+, Docker and Docker Compose, and Ollama with the gemma3:4b model installed.

How is conversation context stored?

Context is stored in a SQLite database managed by the MCP server component.

What transport and protocol does the server use?

The MCP server communicates over HTTP using the JSON‑RPC 2.0 protocol on port 3000; the middleware listens on port 8080.

Can I use this with any MCP client?

Yes, the implementation is fully compatible with any client that adheres to the official MCP specification, including Claude Desktop, VS Code GitHub Copilot, and Cursor.

What authentication or authorization is supported?

The README does not describe any authentication or authorization mechanisms.

Frequently asked questions

What are the runtime requirements?

Python 3.10+, Docker and Docker Compose, and Ollama with the `gemma3:4b` model installed.

How is conversation context stored?

Context is stored in a SQLite database managed by the MCP server component.

What transport and protocol does the server use?

The MCP server communicates over HTTP using the JSON‑RPC 2.0 protocol on port 3000; the middleware listens on port 8080.

Can I use this with any MCP client?

Yes, the implementation is fully compatible with any client that adheres to the official MCP specification, including Claude Desktop, VS Code GitHub Copilot, and Cursor.

What authentication or authorization is supported?

The README does not describe any authentication or authorization mechanisms.

Comments

Basic information

Category

AI & Agents

License

MIT license

Transports

stdio

Author

jorgesandoval

More AI & Agents MCP servers

早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

PDI Bridge for Claude

jxrlabs

Connect Claude Desktop to your ServiceNow PDI. Query records, inspect Business Rules, review ACLs, and troubleshoot against your live instance.

Competitor Tracker & Co.

Competitor Tracker & Co.

Competitor Tracker & Co. watches your competitors' websites and tells you what changed. Every week it crawls their pricing, product, messaging and corporate pages, detects the changes that matter, and files a tagged, ran