Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
Ollama MCP server exists for a simple reason — assistants are far more useful when they can act on Ollama directly instead of describing what you should do. Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
This isn't a generic "wrap the Ollama API" server. Each tool ships with a baked-in system prompt and a description written for the calling agent, so the agent knows when to hand off and gets a tuned result back without re-stating instructions every call.
Installation goes through your MCP client rather than a global install: point it at ollama-handoff on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Once Ollama is connected, these are the calls the assistant has available:
ask_local — One-shot prompt to the local modelchat_local — Multi-turn local chatsummarize_local — Structured summary (headline + bullets)code_review_local — Quick first-pass review of a diff/codedraft_commit_message_local — Conventional commit message from a diffextract_local — Pull structured items from unstructured textlist_models — List locally available Ollama modelsserver_info — Report the effective configurationYou will need 2 environment variables: OLLAMA_DEFAULT_MODEL, OLLAMA_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
ollama serve) with at least one model pulled, e.g. ollama pull qwen2.5-coder:14b. - Python 3.11+ (or just uvx, which manages it for you).Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Ollama's toolset — ask_local, chat_local, summarize_local and 5 more — is a fair guide to whether it matches your workflow. It is maintained by Michael-WhiteCapData; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| ask_local | One-shot prompt to the local model |
| chat_local | Multi-turn local chat |
| summarize_local | Structured summary (headline + bullets) |
| code_review_local | Quick first-pass review of a diff/code |
| draft_commit_message_local | Conventional commit message from a diff |
| extract_local | Pull structured items from unstructured text |
| list_models | List locally available Ollama models |
| server_info | Report the effective configuration |
{
"mcpServers": {
"ollama-handoff": {
"command": "uvx",
"args": ["ollama-handoff"],
"env": {
"OLLAMA_DEFAULT_MODEL": "qwen2.5-coder:14b"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
ollama serve) with at least one model pulled, e.g. ollama pull qwen2.5-coder:14b. - Python 3.11+ (or just uvx, which manages it for you).| Variable | Description | Required |
|---|---|---|
| OLLAMA_DEFAULT_MODEL | Configuration value read at startup. | Optional |
| OLLAMA_URL | Endpoint or connection string the server talks to. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.