MCP Agent Toolkit

Run SQL, APIs, and sandboxed Python for multi-step research and data tasks.

License

MIT License

Source

third_party_registry

Updated

2026-10-18

// securityCaution

Runs locally
Open source
Licensed· MIT License

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

No copy-paste install info for "MCP Agent Toolkit" yet — see the docs or source repo.

// examples

Combine querying and data analysis

Prompt

Connect to the read-only database and query sales by region for the last 30 days. Then call the internal REST API to fetch campaign data. Use Python to calculate sales changes before and after each campaign, and output a table with conclusions.

Expected

SQL results, a merged analysis table, and a brief conclusion on campaign effectiveness.

Validate and clean API data

Prompt

Call the specified REST API to fetch user behavior data, check for missing values, duplicate records, and abnormal fields. Use Python to produce a summary of the cleaned CSV and list the data quality issues found.

Expected

A data quality report, cleaning summary, and a description of the structured data ready for further processing.

Orchestrate a multi-step research task

Prompt

First use an API to fetch public metrics for an industry, then query internal historical data with read-only SQL, and use Python for year-over-year and trend analysis. Finally, compile a research summary with key findings and next-step recommendations.

Expected

A concise report with external vs. internal data comparisons, trend analysis, and research recommendations.