LABSCO SUMMARY

This is scaffolding for a model that is too small, which makes it useful in exactly one situation and pointless in the others.

The premise is honest and narrow: a 4B model fails structured reasoning not because it lacks the steps but because nothing makes it take them, and enforcing the structure externally recovers some of that. If you are running a small local model — for cost, for privacy, for offline work — that is a real gain. If you are already calling a frontier model, the scaffolding adds latency to something the model does natively. Worth deciding which situation you are in before attaching it, because the tool cannot tell you and will happily wrap either.

What it is

A single-tool reasoning harness: it takes a problem and enforces an agentic chain-of-thought with adaptive parsing, aimed at making small models work methodically rather than answering from pattern.

What you get

solve_problem enforces the step-by-step structure rather than requesting it, which is the difference between a prompt that suggests reasoning and a harness that requires it.
The README's own example is SEND + MORE = MONEY — a cryptarithmetic puzzle with eight unique digits, five columns and four carries — which a bare 4B model does not solve.

Requirements

MODEL, naming the model to drive, and a current Node runtime.

Setup effort

One command — npm install @slbdn/cotforce-mcp

See installation options

USE CASES

01

Getting a small local model through a structured problem

Hand it the problem and let the harness force the steps, rather than hoping a prompt asking for reasoning produces any.

solve_problem

1 tool

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`solve_problem`

Solves a problem using strict Agentic Chain-of-Thought with adaptive parsing, retry logic, token budgeting (via tiktoken), and configurable model.

BEFORE YOU INSTALL

What to know first

Tools you get

1 tool when we connected.

Requires

npx on PATH

CONTEXT COST

Light Standing cost

Rated by the size of the one tool definition that rides along on every turn

INSTALLATION

Connect your client

Server setup

TERMINAL

npm install @slbdn/cotforce-mcp

MCP Clients

Claude Desktop — npx

CLAUDE DESKTOP — NPX · JSON

{
  "mcpServers": {
    "cotforce": {
      "command": "npx",
      "args": [
        "-y",
        "@slbdn/cotforce-mcp"
      ],
      "env": {
        "MODEL": "claude-3-5-sonnet"
      }
    }
  }
}

Claude Desktop — local build

Clone and build the server:

CLAUDE DESKTOP — LOCAL BUILD · TERMINAL

git clone https://github.com/islobodan/cotforce-mcp
cd cotforce-mcp
npm install
npm run build

Then add this; <YOUR_PATH_TO_COTFORCE_MCP> is the full path of the cotforce-mcp folder you cloned:

CLAUDE DESKTOP — LOCAL BUILD · JSON

{
  "mcpServers": {
    "cotforce": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_COTFORCE_MCP>/index.js"
      ],
      "env": {
        "MODEL": "claude-3-5-sonnet",
        "MAX_RETRIES": "2"
      }
    }
  }
}

Any MCP client — direct LLM mode

Clone and build the server:

ANY MCP CLIENT — DIRECT LLM MODE · TERMINAL

git clone https://github.com/islobodan/cotforce-mcp
cd cotforce-mcp
npm install
npm run build