How to Analyse Stop-and-Search Data with Claude
Analyse UK stop-and-search records with Claude and ToolRouter. Policing data by location, ethnicity, and outcome.
Tool
Claude can interpret stop-and-search data through multiple lenses — calculating outcome rates by demographic group, identifying whether search rates in an area correlate with crime levels, and flagging statistical patterns that warrant further investigation. It brings analytical rigour to a dataset that is easy to misread without contextual interpretation.
Connect ToolRouter to Claude
1Open connector settings Open Settings
2Add a custom connector with these details
Name
ToolRouterURL
https://api.toolrouter.com/mcp3Let Claude set you up Open Claude
Steps
Once connected (see setup above), use the Crime Stats tool:
- Ask: "Get stop-and-search data for Hackney for the past six months using crime-stats"
- Claude returns records with outcomes, demographics, and legislation used
- Ask: "What percentage of stops resulted in an arrest, broken down by self-defined ethnicity?"
- Request: "Are there any patterns here that would be worth investigating further?"
Example Prompt
Try this with Claude using the Crime Stats tool
Pull stop-and-search records for Brixton for January to June 2024. Calculate outcome rates by demographic group and flag any statistically notable disparities.
Tips
- Compare outcome rates across demographic groups rather than raw stop counts for a fairer analysis
- Ask Claude to note sample size limitations — small counts can produce misleading percentages
- Combine with local crime data to contextualise whether stop rates reflect crime patterns