CrashStory MCP
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., "@CrashStory MCP Find crashes in Denver last month"
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.
CrashStory MCP
Hosted, read-only MCP server for Colorado crash data, attorney discovery, and AI-analyzed review intelligence.
Install page: https://crashstory.com/mcp
Examples: https://crashstory.com/mcp/examples
Manifest: https://crashstory.com/.well-known/mcp/server.json
Hosted endpoint: https://crashstory-mcp-production.up.railway.app/mcp
CrashStory MCP is built for Claude, Cursor, Windsurf, Gemini CLI, ChatGPT Actions, and other compatible AI clients. The goal is simple: make CrashStory's structured Colorado crash and attorney data directly usable in modern AI workflows.
What It Does
Search Colorado crash records
Pull a crash detail record with richer context
Search Colorado personal injury attorneys
Compare attorney profiles and review intelligence
Search attorney reviews for specific needs, concerns, or case types
Find crash activity near a law office
Related MCP server: Slack MCP Server
Quick Start
Claude Code
claude mcp add --transport http crashstory https://crashstory-mcp-production.up.railway.app/mcpCursor
{
"mcpServers": {
"crashstory": {
"url": "https://crashstory-mcp-production.up.railway.app/mcp"
}
}
}Windsurf
{
"mcpServers": {
"crashstory": {
"serverUrl": "https://crashstory-mcp-production.up.railway.app/mcp"
}
}
}Gemini CLI
{
"mcpServers": {
"crashstory": {
"httpUrl": "https://crashstory-mcp-production.up.railway.app/mcp"
}
}
}ChatGPT Actions
Import this OpenAPI file:
https://crashstory.com/mcp/gpt-actions-openapi.json
Public Links
Install page: https://crashstory.com/mcp
Prompt gallery: https://crashstory.com/mcp/examples
Status page: https://crashstory.com/mcp/status
llms.txt: https://crashstory.com/llms.txtAttorney directory: https://crashstory.com/lawyers
Find an accident: https://crashstory.com/find-accident
Live incidents: https://crashstory.com/accidents/live
Statistics: https://crashstory.com/statistics
Rankings: https://crashstory.com/rankings
Example Prompts
See examples/prompts.md or the live gallery at https://crashstory.com/mcp/examples
Tool Categories
Attorney discovery
search_attorneyslist_attorney_citiesfind_nearby_attorneysget_attorney_leaderboardget_attorney_profilecompare_attorneys
Review intelligence
get_attorney_reviewsget_review_analyticsget_review_intelligencecompare_review_intelligenceget_city_review_leaderboardsearch_attorney_reviews
Crash data
search_crashesget_crash_detailsget_nearby_crashes
Local Development
npm install
npm run typecheck
npm run build
npm run dev:httpNotes
The primary public transport is stateless Streamable HTTP.
The server is intentionally read-only.
This repository is the public MCP surface only. The broader CrashStory application remains private.
License
MIT
Available Tools
15 toolscompare_attorneysA
Compare 2-4 attorney profiles side-by-side. Use canonical slugs from search_attorneys. Returns key comparison metrics including ratings, reviews, specialties, practice areas, and known experience fields.
Inputs: slugs (required).
compare_review_intelligenceA
Compare AI-analyzed review intelligence across 2-5 law firms. Returns side-by-side pain point dimensions, sentiment, trust signals, response quality, and case type distributions for competitive analysis.
Inputs: firm_slugs (required).
find_nearby_attorneysA
Find personal injury attorneys near a geographic location. Uses Haversine distance calculation. Returns attorneys sorted by distance with contact info and ratings.
Inputs: latitude (required), longitude (required), limit, radius_miles.
get_attorney_leaderboardA
Get the top-ranked personal injury attorneys in Colorado. Returns attorneys ranked by a composite score considering ratings, reviews, experience, and case outcomes.
Inputs: limit.
get_attorney_profileA
Get a detailed attorney profile by slug. Returns full bio, practice areas, reviews, credentials, office location, and AI-analyzed intelligence data when available.
Inputs: slug (required).
get_attorney_reviewsA
Get paginated client reviews for a specific attorney. Includes review text, rating, reviewer name, date, and rating distribution breakdown.
Inputs: slug (required), page, limit.
get_city_review_leaderboardA
Get the review-based leaderboard for attorneys in a specific Colorado city. Ranks attorneys by composite review metrics including velocity, freshness, momentum, and rating.
Inputs: city (required), limit.
get_crash_detailsA
Get full details of a specific Colorado crash by its CUID (Crash Unique Identifier). Returns complete crash record including all vehicles involved, injuries, contributing factors, road conditions, weather, and narrative.
Inputs: cuid (required).
get_nearby_crashesA
Get crash records near a specific attorney's office location. This tool is attorney-centered, not a raw lat/lng search. Use a canonical attorney slug from search_attorneys, then this tool will search around that office address.
Inputs: attorney_slug (required), sort, limit, months, +1 more.
get_review_analyticsB
Get review velocity analytics for a specific attorney. Includes review frequency trends, freshness score, momentum indicators, composite score, city percentile rank, and month-over-month time series.
Inputs: slug (required).
get_review_intelligenceA
Get AI-analyzed review intelligence for a law firm. Returns plain-language praise and complaint summaries, 12 consumer pain point dimensions, case type distribution, trust signals, response quality, and highlight reviews.
Inputs: firm_slug (required).
list_attorney_citiesA
List all Colorado cities that have active personal injury attorneys, with the count of attorneys in each city. Useful for discovering which cities have coverage.
Inputs: no named parameters.
search_attorney_reviewsA
Search a law firm's detailed reviews for the most relevant matches to a specific need, case type, injury, sentiment, or pain point. Use this when someone asks for reviews about communication, wrongful death, motorcycle crashes, fees, settlement clarity, or similar client concerns.
Inputs: firm_slug (required), need, limit, injury, +3 more.
search_attorneysA
Search for personal injury attorneys in Colorado. Filter by city, county, specialty, rating, and verification status. Returns attorney profiles plus the canonical slug to use with profile, review, and comparison tools.
Inputs: city, page, limit, query, +5 more.
search_crashesA
Search Colorado crash records by location, date range, crash type, and severity. Database contains 500,000+ CDOT crash records. Returns key fields including location, date, severity, injuries, fatalities, and contributing factors.
Inputs: limit, date_to, location, severity, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Most tools target distinct actions, but the review-related tools (get_attorney_reviews, get_review_analytics, get_review_intelligence, compare_review_intelligence, search_attorney_reviews) overlap significantly and could confuse an agent. Descriptions help, but boundaries are not immediately clear.
Tool names generally follow a verb_noun pattern (get_, search_, compare_, list_, find_), but 'find_nearby_attorneys' is a minor deviation from the search_ convention. Otherwise consistent and predictable.
15 tools is at the upper end of the well-scoped range. The dual domain (attorneys and crashes) justifies the count, but the five review-intelligence tools feel slightly heavy and could be consolidated.
The tool surface covers attorney discovery, profiling, reviews, analytics, and crash records extensively. A minor gap is the lack of a direct tool to connect crashes to attorneys (only attorney-to-crash via get_nearby_crashes), but overall workflows are not dead-ended.
Maintenance
Related MCP Connectors
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Connect AI to millions of laws and court cases with the Lawstronaut MCP.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Hybrid human + AI expertise for faster, trusted answers and decisions via MCP Server.
Related MCP Servers
- AlicenseAqualityCmaintenanceAn MCP server providing AI assistants access to Canadian case law and legislation metadata from CanLII across all jurisdictions, supporting search and citation relationships.735 npm8MIT
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server that enables AI assistants to access Slack workspace data, including channels, messages, threads, and user information.53,839 npm3MIT
- AlicenseAqualityDmaintenanceA read-only MCP server that provides AI coding tools with database schema structure (tables, columns, keys, relationships) without exposing row data.3Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server for PDF analysis that enables text extraction, image extraction, metadata retrieval, and text search via natural language.MIT