{"id":"npstorey-civic-ai-tools","name":"civic-ai-tools","af_score":63.0,"security_score":46.8,"reliability_score":26.2,"what_it_does":"An open-source toolkit that connects AI assistants to civic/public data sources via the Model Context Protocol (MCP). It includes (or wires up) MCP servers for Socrata-based NYC Open Data (e.g., 311, inspections, housing) and Google Data Commons, enabling natural-language querying and generation of analyses/visualizations against live civic datasets.","best_when":"You want an MCP-based adapter experience for civic open data and will work within a developer/local environment (or GitHub Codespaces) to configure API keys and run the MCP servers.","avoid_when":"You need a standard REST/SDK interface with explicit OpenAPI contracts, strict idempotency guarantees, and clearly documented operational/retry semantics.","last_evaluated":"2026-03-30T15:37:22.204058+00:00","has_mcp":true,"has_api":false,"auth_methods":["API key (SOCRATA_APP_TOKEN for Socrata/NYC Open Data)","API key (DC_API_KEY for Data Commons)"],"has_free_tier":false,"known_gotchas":["Without API keys, rate limits are lower (Data Commons is skipped without DC_API_KEY; NYC Open Data queries still work with reduced limits).","Local setup requires building MCP servers and generating config; agents may fail if servers/tools are not correctly started/registered in the client."],"error_quality":0.0}