
CrashStory MCP server
Which MCP servers are CrashStory's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.crashstory/crashstoryverified in the MCP registry
The registry name sits under crashstory.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools18
- Server calls itselfcrashstory
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 85 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- For "locate a possible crash record by place and date", the likely first call is search_crashes.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer104 ms
- Space in an agent's context≈ 3,351 tokensthe definitions of all its tools (18), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 18 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 18 of 18
What an agent can do with it
- can do · locate a possible crash record by place and date
- not sure · check a crash record against your own details
- not sure · find the agency to request a police report from
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_attorneysSearch 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.
get_attorney_profileGet a detailed attorney profile by slug. Returns full bio, practice areas, reviews, credentials, office location, and AI-analyzed intelligence data when available.
find_nearby_attorneysFind personal injury attorneys near a geographic location. Uses Haversine distance calculation. Returns attorneys sorted by distance with contact info and ratings.
list_attorney_citiesList all Colorado cities that have active personal injury attorneys, with the count of attorneys in each city. Useful for discovering which cities have coverage.
get_attorney_leaderboardGet the top-ranked personal injury attorneys in Colorado. Returns attorneys ranked by a composite score considering ratings, reviews, experience, and case outcomes.
compare_attorneysCompare 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.
get_attorney_reviewsGet paginated client reviews for a specific attorney. Includes review text, rating, reviewer name, date, and rating distribution breakdown.
get_review_analyticsGet 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.
get_city_review_leaderboardGet the review-based leaderboard for attorneys in a specific Colorado city. Ranks attorneys by composite review metrics including velocity, freshness, momentum, and rating.
get_review_intelligenceGet 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.
compare_review_intelligenceCompare 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.
search_attorney_reviewsSearch 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…
search_crashesSearch 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.
get_crash_detailsGet 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.
get_nearby_crashesGet 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.
list_research_datasetsList CrashStory research datasets that can be queried through the MCP server, including gas-price analysis datasets and their available data views.
get_research_dataset_summaryGet the structured summary/report for a CrashStory research dataset. Use this before row-level querying to understand coverage, methodology, findings, and limitations.
query_research_datasetQuery rows from CrashStory research datasets. Supports the gas-price analysis datasets with optional state, year, and month filters so agents can perform their own follow-on analysis.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"crashstory": {
"type": "http",
"url": "https://crashstory-mcp-production.up.railway.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http crashstory https://crashstory-mcp-production.up.railway.app/mcpclaude.ai, ChatGPT and other clients: add https://crashstory-mcp-production.up.railway.app/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.