A
licenseA
qualityA
maintenanceLocal-first MCP server that gives any AI coding agent per-project memory, workflow intelligence, and always-on, lossless token & context optimization.
37
18
4
MIT
ollama-mcp
by DTG404
Provides tools for generating code, commit messages, documentation, task classification, file summarization, and issue triage using local Ollama models with VRAM-aware model selection.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ollama-mcpdraft a basic Express.js route handler for a user API"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ollama-mcp
VRAM-aware MCP server that offloads token-heavy development tasks to local Ollama models, saving API tokens for complex reasoning.
Tools
Tool | Description |
| Generate boilerplate and scaffolding |
| Write commit messages from diffs |
| Draft documentation and prose |
| Auto-route work to the right agent type |
| Summarize unfamiliar source files |
| Classify and prioritize issues |
| List available Ollama models |
| Check for model updates |
| Show current configuration |
Related MCP server: token-diet
VRAM Management
The server monitors GPU memory via nvidia-smi and selects models based on available VRAM. Models are loaded on demand.
Setup
npm installRequires Ollama running locally with models pulled.
Usage
npm startConfigure in Claude Code MCP settings:
{
"mcpServers": {
"ollama": {
"command": "node",
"args": ["/path/to/ollama-mcp/index.js"]
}
}
}Tech Stack
Node.js (>=18)
@modelcontextprotocol/sdkZod for schema validation
Ollama API for local model inference
nvidia-smifor VRAM monitoring
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
An MCP server that gives your AI access to the source code and docs of all public github repos
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Cloud-hosted MCP server for durable AI memory
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAn MCP server that reduces token usage by injecting graph-ranked repo maps, decision logs, and diff-only output into AI coding tool requests.1MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that reduces AI coding agent token usage by 80-99% through a queryable knowledge graph of code, change tracking, and persistent memory across sessions.1011MIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that lets AI agents delegate domain-specific tasks to local Ollama models, using purpose-built specialists for structured tasks like config generation, parsing, and validation.-