QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / CT Injury Cases

CT Injury Cases

Q: Is CT Injury Cases MCP server safe?

QAmcp's test on 30 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 12 of its 14 tools are labeled read-only; the others may change or send things. Overall it scored 89/100 on 30 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by ctinjurycases.com · https://ctinjurycases.com/mcp

Connecticut personal injury litigation data: car accident cases, Hartford Judicial District.

14 tools✓ no account neededPricing: not listed

Visit website

89 /100

PASS · WITH NOTES

12 of 12 checks · 30 Oct 2026

Is CT Injury Cases MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
12 of its 14 tools are labeled read-only; the others may change or send things.
Overall it scored 89/100 on 30 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

14 tools, in the server's own words.

describe_datasetread-only

Start here.

search_casesread-only

List auto-injury cases matching filters, in docket-number order, up to 50 per page.

get_caseread-only

One case: dates, disposition, trial, verdict and offer amounts, its motion rulings, and the judges, attorneys and law firms by side.

statsread-only

Compute one metric over cases (or motion rulings), optionally broken down by up to two dimensions and narrowed by filters.

search_judgesread-only

List judges by name and district, with case counts, most cases first.

get_judgeread-only

One judge: how the cases they decided ended (closures in the last ~11 months), motion grant rates by motion family, and trial and verdict figures.

search_firmsread-only

List law firms by name, side, district and size, most cases first.

get_firmread-only

One law firm: its attorneys, the firms it most often faces, the medical experts named for its side, its motion practice, and how its cases ended.

search_attorneysread-only

List attorneys by name, firm, side and district, most cases first.

get_attorneyread-only

One attorney: their firms, the firms they most often face, the medical experts named for their side, their motion practice, and how their cases ended.

search_providersread-only

List medical providers named in expert disclosures, by type, specialty, side (treating or defense examiner), town and size, most cases first.

get_providerread-only

One medical provider: the law firms that named them, their case list, how those cases ended, and, for defense examiners, the kinds of findings they disputed an…

request_data

Tell us about data this dataset does not have but you need: other courts or states, case types, fields, documents.

send_message

Send a message to the person who runs this service: feedback, a question, a problem with the data, or interest in paid features, broader coverage or higher lim…

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Ready for the newest MCP version
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
3 warnings
- !search_firms and search_attorneys have nearly the same description (79% of their words are shared; the only difference: "law", "size" vs "attorney"), so an AI may not know which to pick
- !search_judges and search_attorneys have nearly the same description (64% of their words are shared; the only difference: "judge", "count" vs "attorney", "firm", "side"), so an AI may not know which to pick
- !search_judges and search_firms have nearly the same description (60% of their words are shared; the only difference: "judge", "count" vs "firm", "law", "side"), so an AI may not know which to pick
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !The tool list is about 72 KB (roughly 18k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
✓
ConnectsConnected in 1.1 s
pass
✓
Lists its toolsFound 14 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Tools work with good inputs
All good
- ✓describe_dataset: Worked (706 ms)
- ✓search_cases: Worked (199 ms)
- ✓get_case: Answered with an error, probably because of our sample input: No case TEST in the dataset. Docket numbers look like HHD-CV-21-6140000-S; search_cases lists them.
- ✓stats: Worked (132 ms)
- ✓search_judges: Worked (130 ms)
- ✓get_judge: Answered with an error, probably because of our sample input: No judge test; search_judges lists judge keys.
- ✓search_firms: Worked (145 ms)
- ✓get_firm: Answered with an error, probably because of our sample input: No firm with juris number https://example.com; search_firms lists them.
- and 6 more
pass
✓
Bad inputs give a clean error
All good
- ✓describe_dataset: Refused wrong type for "purpose" with a clear error
- ✓search_cases: Refused wrong type for "district" with a clear error
- ✓get_case: Refused missing required input "docket_number" with a clear error
- ✓get_case: Refused wrong type for "docket_number" with a clear error
- ✓stats: Refused missing required input "metric" with a clear error
- ✓stats: Refused wrong type for "metric" with a clear error
- ✓search_judges: Refused wrong type for "name" with a clear error
- ✓get_judge: Refused missing required input "judge_key" with a clear error
- and 10 more
pass
✓
Tools work together
3 chains working
- ✓search_judges → search_cases: search_cases found what search_judges returned (judge_key = "MORGAN|L")
- ✓search_judges → get_judge: get_judge found what search_judges returned (judge_key = "MORGAN|L")
- ✓search_providers → get_provider: get_provider found what search_providers returned (provider_id = "practice:jeffersonradiology")
pass
✓
Fast enough
All good
- ✓Connecting took 1.1 s
- ✓Listing tools took 51 ms
- ✓Average tool answer: 211 ms
- ✓describe_dataset: Slowest tool: describe_dataset (706 ms)
pass
✓
No secrets leakedChecked 26 error messages: no secrets or internal details
pass

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://ctinjurycases.com/mcp

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

[![QAmcp score](https://qamcp.dev/s/com-ctinjurycases-ct-injury-cases.svg)](https://qamcp.dev/s/com-ctinjurycases-ct-injury-cases.html)

Score over time

30 Oct 202689

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use CT Injury Cases, signed in with GitHub, one per person. Reviews never change the score.

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works