MCP Server

Name: Quelltest
Author: Shashank Bindal

Quell ships a Model Context Protocol (MCP) server that exposes its tools to any MCP-compatible AI agent.

Install

pip install "quelltest[mcp]"

Start

quell-mcp
# Listening on http://localhost:8765

Tools

Tool	Description
`check_requirements`	Scan a file for requirement gaps
`reproduce_bug`	Convert a bug description to a failing test
`prove_coverage`	Get requirement coverage score for a file
`get_project_score`	Get project-wide Quell Score

For full usage examples and agent configuration, see AI Agents guide.

MCP tool schemas

`check_requirements`

{
  "name": "check_requirements",
  "description": "Scan a file or directory for uncovered requirements",
  "inputSchema": {
    "type": "object",
    "properties": {
      "target": { "type": "string", "description": "file or directory path" },
      "fix": { "type": "boolean", "description": "generate verified tests for gaps" }
    },
    "required": ["target"]
  }
}

`reproduce_bug`

{
  "name": "reproduce_bug",
  "description": "Convert a plain-English bug description into a verified failing test",
  "inputSchema": {
    "type": "object",
    "properties": {
      "description": { "type": "string", "description": "bug description in plain English" },
      "file": { "type": "string", "description": "optional target source file" }
    },
    "required": ["description"]
  }
}

`get_project_score`

{
  "name": "get_project_score",
  "description": "Get requirement coverage score for the project or a single file",
  "inputSchema": {
    "type": "object",
    "properties": {
      "file_path": { "type": "string", "description": "optional — filter to one file" }
    }
  }
}