automation-audit
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., "@automation-audit Walk me through an automation audit for our monthly invoice processing."
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.
Automation Audit MCP
An MCP server that helps AI assistants evaluate business processes for automation. It collects structured discovery answers, estimates manual labor cost, scores automation potential, and stores completed audits in SQLite.
What it does
The server exposes tools that let an MCP client:
create businesses and the processes they want to evaluate;
calculate monthly hours and labor cost for repetitive work;
score automation potential using frequency, rule clarity, data readiness, process stability, and required human judgment;
save discovery answers and completed audit recommendations;
list saved audits and retrieve a complete audit with its discovery answers.
It also includes a start_automation_audit prompt that guides the assistant
through the assessment without inventing missing information or saving results
before the user confirms them.
Related MCP server: dingdawg-finance-agent
Available tools
Tool | Purpose |
| Estimate monthly hours and labor cost. |
| Produce a 0–100 automation score and category. |
| Store a business being audited. |
| Store a process associated with a business. |
| Save or update one discovery response. |
| Store a validated completed audit. |
| List saved audits, newest first. |
| Retrieve an audit and all related discovery answers. |
Requirements
Python 3.12 or newer
An MCP-compatible client
Run locally
git clone https://github.com/zuperRuslana/automation-audit-mcp.git
cd automation-audit-mcp
uv sync
uv run python main.pyThe server communicates over standard input/output, so it is normally started by an MCP client rather than used directly in a terminal.
MCP client configuration
Add a server entry like this to your MCP client configuration, replacing the directory with the absolute path where you cloned the project:
{
"mcpServers": {
"automation-audit": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/automation-audit-mcp",
"run",
"python",
"main.py"
]
}
}
}Example workflow
Create a business with
create_business.Create a process using the returned business ID.
Record discovery responses with
save_discovery_answer.Calculate time and labor cost with
calculate_time_cost.Calculate suitability with
calculate_automation_score.Review the recommendation and confirm it with the user.
Save the result with
save_audit.Retrieve the complete record with
get_audit.
Data and validation
Audit data is stored locally in automation_audits.db. The database file is
ignored by Git, so business data is not uploaded with the source code.
The server rejects negative cost inputs, ratings outside the supported range, orphaned database records, and audit categories that conflict with their score.
Tests
uv run pytestThe regression suite covers startup, input validation, database connection safety, foreign-key enforcement, and audit consistency.
Project structure
automation-audit-mcp/
├── main.py # MCP server entry point
├── server.py # Tools, prompt, validation, and SQLite storage
├── tests/ # Regression tests
├── pyproject.toml # Python package and dependency metadata
└── uv.lock # Reproducible dependency lock fileAvailable Tools
8 toolscalculate_automation_scoreC
Calculate how suitable a business process is for automation.
Inputs: frequency (required), rule_clarity (required), data_readiness (required), process_stability (required), +1 more.
calculate_time_costB
Calculate the monthly time and labor cost of a manual process.
Inputs: hourly_cost (required), minutes_per_task (required), frequency_per_week (required). Returns: object
create_businessC
Create and store a business for an automation audit.
Inputs: name (required), industry (required), employee_count (required).
create_processC
Create a business process to evaluate for automation.
Inputs: name (required), business_id (required), description (required).
get_auditB
Retrieve one complete automation audit.
Inputs: audit_id (required).
list_auditsA
List all saved automation audits.
Inputs: no named parameters. Returns: result
save_auditB
Save the completed automation audit for a process.
Inputs: category (required), process_id (required), monthly_hours (required), recommendation (required), +2 more.
save_discovery_answerC
Save or update a discovery answer for a business process.
Inputs: process_id (required), answer_text (required), question_key (required), question_text (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct resource or action: calculations, creation, saving answers/audits, and listing/retrieving audits. Even similar verbs like create_business and create_process are clearly separated by the object they operate on.
All tool names follow a consistent verb_noun snake_case pattern, such as calculate_, create_, save_, list_, and get_. This makes the set predictable and easy to navigate.
Eight tools is a well-scoped set for an automation audit workflow. Each tool serves a clear purpose in the process from creating businesses and processes to calculating metrics and managing completed audits.
The core audit lifecycle is covered: create businesses/processes, capture discovery answers, calculate cost and automation score, and save/retrieve audits. Minor gaps exist around updating or deleting businesses/processes, but these are not essential to the main workflow.
Maintenance
Related MCP Connectors
Plan automation pilots, estimate illustrative ROI and prioritize workflows. Public, no account.
AI strategy, workflow automation, and process-improvement assessment for small businesses.
Automate tasks, processes, and approvals with AI.
Takes a business process apart and says what to automate first. Eight questions free, 43 paid.
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables managing audit findings in a SQLite database via natural language, allowing queries and updates without writing SQL.3-
- AlicenseAqualityDmaintenanceEnables AI assistants to perform financial analysis, budget forecasting, compliance checks, expense categorization, and risk assessment, returning structured JSON with audit-ready governance receipts.5102 npm1Business Source 1.1

inite-diagnosticofficial
AlicenseAqualityCmaintenanceEnables agents to conduct a structured business process audit, calculating current costs, identifying bottlenecks, and recommending what to automate next, with both local no-account tools and a full remote audit.248 npmMIT- AlicenseNot gradedqualityBmaintenanceEnables multi-agent system auditing with seven-layer analysis, cost governance, compliance mapping, and watchdog monitoring. Offers tools for audit execution, cost analysis, report verification, regulation lookup, remediation suggestions, and fix tracking.1MIT