Hartford Auto-Injury Case Data MCP server
Which MCP servers are Hartford Auto-Injury Case Data'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 2026-10-30
- Registry namecom.ctinjurycases/ct-injury-casesverified in the MCP registry
The registry name sits under ctinjurycases.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-30
- Tools14
- Server calls itselfct-injury-cases
- Server version1.20260909.20261030
- Protocol version2025-06-18
On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 376 ms.
- Its tools do every use case we checked: compare settlement rates against cases that go to trial; check how long Hartford auto injury cases typically take.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- For "compare settlement rates against cases that go to trial", the likely first call is stats.
- Keep approval on for send_message: they delete, send or pay without saying so.
- send_message change data without a sign-in: anyone with the address can call them.
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
- What an agent can do with it2 of 2 use cases
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer580 ms
- Space in an agent's context≈ 3,813 tokensthe definitions of all its tools (14), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results14 of 14 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · estimate typical verdict amounts for a given injury type
- can do · compare settlement rates against cases that go to trial
- can do · check how long Hartford auto injury cases typically take
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
- Tools that delete, send or pay, marked as not destructive: send_message
- Tools that change data, on a server that answers without a sign-in: send_message
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 →
describe_datasetStart here. What the dataset covers (Connecticut Superior Court motor vehicle personal injury cases, Hartford Judicial District) and how current it is, every field, every stats metric and dimension, caveats, and example calls for each tool.
search_casesList auto-injury cases matching filters, in docket-number order, up to 50 per page. Use get_case for one case in full and stats for counts, rates and amounts across many.
get_caseOne case: dates, disposition, trial, verdict and offer amounts, its motion rulings, and the judges, attorneys and law firms by side.
statsCompute one metric over cases (or motion rulings), optionally broken down by up to two dimensions and narrowed by filters. describe_dataset lists every metric and dimension and which unit each applies to. Groups of three or fewer cases…
search_judgesList judges by name and district, with case counts, most cases first. get_judge gives one judge in full.
get_judgeOne 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_firmsList law firms by name, side, district and size, most cases first. get_firm gives one firm in full.
get_firmOne 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. A firm's case counts (cases, plaintiffCases, defenseCases) cover every case it appeared in…
search_attorneysList attorneys by name, firm, side and district, most cases first. get_attorney gives one attorney in full.
get_attorneyOne attorney: their firms, the firms they most often face, the medical experts named for their side, their motion practice, and how their cases ended. An attorney's figures span every firm the attorney has filed with, not only their…
search_providersList medical providers named in expert disclosures, by type, specialty, side (treating or defense examiner), town and size, most cases first. get_provider gives one provider in full.
get_providerOne 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 and on which body regions (counts only).
request_dataTell us about data this dataset does not have but you need: other courts or states, case types, fields, documents. Logged and read by the people who build the dataset.
send_messageSend 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 limits. Include the user's name or email only with their explicit permission.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"ct-injury-cases": {
"type": "http",
"url": "https://ctinjurycases.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http ctinjurycases https://ctinjurycases.com/mcpclaude.ai, ChatGPT and other clients: add https://ctinjurycases.com/mcp as a custom connector in the settings.
OpenAPI spec
14 paths, read 2026-10-30. Open the spec ↗
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.