LabscoMCP early access ↗
NewAITeesMCP SERVER

Ollama Task Decomposition MCP

Puts a local Ollama model behind MCP tools for task decomposition and result evaluation — break a hard problem into subtasks, then score the output against your criteria.

by NewAITees ↗Model Routing, Multi-Model Consultation & Cost ControlCommunity

LABSCO SUMMARY

A second, local model doing the structured thinking.

The point is not to replace your assistant but to give it a place to offload decomposition and evaluation onto a model running on your own hardware — no per-token cost and nothing leaving the machine. It checks at startup whether the configured model exists and warns if not, which saves the confusing failure where every call errors for a reason nobody surfaces.

What it is

An MCP server that sits in front of a local Ollama instance and uses it for structured work rather than chat. The design pairs each tool with a prompt schema: the prompt shapes how the model thinks, the tool carries out the action, so decomposition and evaluation come back structured instead of as prose.

What you get

  • add-task — create a task from name and description, with optional priority, deadline and tags, returning its identifier
  • decompose-task — break a task into subtasks at a granularity of high, medium or low, capped by max_subtasks, returning dependencies and estimated complexity
  • evaluate-result — score a result against a criteria object, with detailed for the long form, returning a score and suggested improvements
  • run-model — run any Ollama model directly with a prompt, temperature and max_tokens
  • Matching prompts, decompose-task and evaluate-result, that give the model the structure each tool expects
  • Resources under three URI schemes — task:// for individual tasks, result:// for evaluations, model:// for the models available
  • Connection pooling and an LRU cache, both sized in config.py, so repeated similar requests do not hit Ollama again
  • Errors that name what went wrong, including the list of available models when the one you asked for is missing

Requirements

A running Ollama with at least one model pulled — ollama pull llama3 is the documented starting point. OLLAMA_HOST defaults to http://localhost:11434, and APP_LOG_LEVEL controls verbosity. The model is chosen in order of precedence: the model parameter on the call, then a model entry in the mcp_config.json inside the clone, then OLLAMA_DEFAULT_MODEL, then the default, llama3. That file ships set to deepseek-r1:14b, and your client starts the server inside the clone, so pull that model, change the entry, or pass model on each call. Run it from a clone: uv sync, then your client starts it with uv --directory pointing at the clone and run ollama-mcp-server. The package is not on PyPI, so there is nothing to pip install.

Setup effort

Build from source — git clone https://github.com/NewAITees/ollama-MCP-server.git

See installation options