Datadog Cost Analyze Agent

MCP server for end-to-end Datadog billable usage and cost analysis.

The server exposes one MCP tool:

• datadog_generate_full_cost_report

This tool runs the full workflow in one call:

1. Fetch billable summary from Datadog
2. Calculate org-level on-demand and committed allocation
3. Generate CSV reports
4. Calculate cost report
5. Return report content as text in the MCP response

Requirements

• Python 3.10+
• Datadog credentials with usage_read permission:
  • DD_API_KEY
  • DD_APP_KEY
  • DD_SITE (optional, defaults to datadoghq.eu)

Install

python3 -m venv .venv
.venv/bin/python -m pip install -r requirements.txt

Publish to PyPI

Package metadata is configured in pyproject.toml. Current package/command names:

• Package: datadog-cost-analyze-agent-mcp
• CLI entrypoint: datadog-cost-analyze-mcp

1) Build distribution files

.venv/bin/python -m pip install --upgrade build twine
.venv/bin/python -m build

This creates:

• dist/*.tar.gz (source distribution)
• dist/*.whl (wheel)

2) Validate package metadata

.venv/bin/python -m twine check dist/*

3) Upload to TestPyPI (recommended first)

.venv/bin/python -m twine upload --repository testpypi dist/*

4) Upload to PyPI

.venv/bin/python -m twine upload dist/*

5) Verify install from PyPI

python3 -m pip install <your-package-name>

Use API tokens for authentication:

• TWINE_USERNAME=__token__
• TWINE_PASSWORD=<pypi-token>

Run with uvx

After publishing to PyPI:

uvx --from datadog-cost-analyze-agent-mcp datadog-cost-analyze-mcp

For local testing before publish:

uvx --from . datadog-cost-analyze-mcp

Run MCP Server

.venv/bin/python mcp_server.py

MCP Tool

datadog_generate_full_cost_report

Arguments

• month (string, required): Month in YYYY-MM format.

Returns

• ok (boolean): Success status
• message (string): Execution summary
• month (string): Month used for the run
• usage_org_count (number): Organization count in usage payload
• final_cost_report_text (string): Final cost CSV content
• detailed_report_text (string): Detailed usage CSV content
• org_summary_report_text (string): Organization summary CSV content
• product_summary_report_text (string): Product summary CSV content
• error (string): Present when ok is false

Generated Files

The workflow also writes default files to .out/:

• .out/billable_summary.json
• .out/billable_detailed_report.csv
• .out/billable_org_summary.csv
• .out/billable_product_summary.csv
• .out/datadog_cost_report.csv

Example MCP Client Config

Using uvx (recommended after publish)

{
  "mcpServers": {
    "datadog-cost-analyze": {
      "command": "uvx",
      "args": ["--from", "datadog-cost-analyze-agent-mcp", "datadog-cost-analyze-mcp"],
      "env": {
        "DD_API_KEY": "your_api_key",
        "DD_APP_KEY": "your_app_key",
        "DD_SITE": "datadoghq.eu"
      }
    }
  }
}

Using local Python directly

{
  "mcpServers": {
    "datadog-cost-analyze": {
      "command": "/absolute/path/to/.venv/bin/python",
      "args": ["/absolute/path/to/mcp_server.py"],
      "env": {
        "DD_API_KEY": "your_api_key",
        "DD_APP_KEY": "your_app_key",
        "DD_SITE": "datadoghq.eu"
      }
    }
  }
}

Pricing Source

Cost calculations are based on Datadog pricing:

• https://www.datadoghq.com/pricing/list/