# CT Injury Cases (remote · ctinjurycases.com)

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

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `ctinjurycases.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases.md), [page](https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases)

## Channel facts

- Endpoint: `https://ctinjurycases.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.20260909.20261030`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2334 tokens (~166/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the CT Injury Cases MCP server?

CT Injury Cases is a hosted endpoint at https://ctinjurycases.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-ctinjurycases-ct-injury-cases 'https://ctinjurycases.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-ctinjurycases-ct-injury-cases": {
      "url": "https://ctinjurycases.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-ctinjurycases-ct-injury-cases": {
      "type": "http",
      "url": "https://ctinjurycases.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-ctinjurycases-ct-injury-cases]
url = "https://ctinjurycases.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-ctinjurycases-ct-injury-cases": {
      "type": "remote",
      "url": "https://ctinjurycases.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-ctinjurycases-ct-injury-cases --url 'https://ctinjurycases.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-ctinjurycases-ct-injury-cases:
    url: "https://ctinjurycases.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-ctinjurycases-ct-injury-cases": {
      "Transport": "http",
      "Url": "https://ctinjurycases.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-ctinjurycases-ct-injury-cases -t streamable-http -u 'https://ctinjurycases.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-ctinjurycases-ct-injury-cases": {
      "type": "http",
      "url": "https://ctinjurycases.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 68, +1)

- [functional] Server version: 1.20260909.20261030 → 2.0.0

### 2026-11-03 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 65, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-30 (score 65)

First indexed and scored.

## MCP tools (14)

### `describe_dataset` (~81 tokens)

Describe the dataset

Start 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.

Input parameters:

- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

Output parameters:

- `caveats` (array): What to keep in mind across the dataset.
- `coverage` (object): What the dataset covers and how current it is.
- `dimensions` (array): Every stats dimension.
- `examples` (array): One example call per tool: the tool name, then its arguments as JSON.
- `fields` (object): Field glossary.
- `metrics` (array): Every stats metric.
- `source` (string): Where the data comes from and where to find a case's official record.

### `search_cases` (~289 tokens)

Search cases

List 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.

Input parameters:

- `case_type` (string): Case type code: V01, V04 or V09.
- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `disposition_category` (string): How the case ended, e.g. withdrawal or plaintiff_verdict; pending for open cases.
- `district` (string): Judicial district, e.g. HARTFORD JD.
- `filed_from` (string): Filed on or after this date (YYYY-MM-DD).
- `filed_to` (string): Filed on or before this date (YYYY-MM-DD).
- `firm_juris_number` (string): Juris number from search_firms; matches either side's lead firm.
- `judge_key` (string): Judge key from search_judges; matches the judge who decided the disposition.
- `limit` (integer): Results per page, at most 50 (the default).
- `litigation_type` (string): third_party, um_uim or subrogation.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.
- `trial_kind` (string): jury, court or not_tried.

Output parameters:

- `nextCursor`: Pass as cursor for the next page; null on the last.
- `results` (array): This page of matches.
- `total` (integer): Matches across all pages.

### `get_case` (~90 tokens)

Case details

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

Input parameters:

- `docket_number` (string, required): Docket number, e.g. HHD-CV-21-6140000-S.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

Output parameters:

- `attorneys` (array): Attorneys who appeared, with their juris numbers for get_attorney.
- `case` (object): The case record.
- `dispositionJudge`: The judge who decided the disposition; null when no judge did.
- `firms` (object): Lead law firm on each side; null when none is known.
- `rulings` (array): Motion rulings in the case.

### `stats` (~449 tokens)

Case statistics

Compute 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 are suppressed. At most 100 groups, largest first.

Input parameters:

- `amount_in_demand` (string): Amount-in-demand band, e.g. 15000_or_more.
- `case_type` (string): Case type code: V01, V04 or V09.
- `claims_lost_wages` (boolean): Lost wages are claimed.
- `commercial_vehicle` (boolean): A commercial vehicle was involved.
- `disposition_category` (string): How the case ended, e.g. withdrawal or plaintiff_verdict; pending for open cases.
- `district` (string): Judicial district, e.g. HARTFORD JD.
- `filed_from` (string): Filed on or after this date (YYYY-MM-DD).
- `filed_to` (string): Filed on or before this date (YYYY-MM-DD).
- `firm_juris_number` (string): Juris number from search_firms; matches either side's lead firm.
- `group_by` (array): Up to two dimensions to break the metric down by.
- `injury_kind` (string): An alleged injury kind, e.g. fracture.
- `injury_region` (string): An injured body region, e.g. neck.
- `judge_key` (string): Judge key from search_judges; matches the judge who decided the disposition.
- `litigation_type` (string): third_party, um_uim or subrogation.
- `mechanism` (string): How the crash happened, e.g. rear_end.
- `metric` (string, required): What to compute; see describe_dataset for each metric.
- `plaintiff_role` (string): driver, passenger, pedestrian…
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.
- `road_type` (string): Kind of road, e.g. interstate.
- `trial_kind` (string): jury, court or not_tried.
- `um_uim` (boolean): UM/UIM coverage is claimed.

Output parameters:

- `closedFrom`: For metrics over closed cases, the first disposition date counted, inclusive; the figures are not all-time. Null for metrics over every case.
- `closedTo`: For metrics over closed cases, the last disposition date counted, inclusive: the as-of date. Null for metrics over every case.
- `groupBy` (array): The group_by dimensions, in order.
- `groups` (array): One entry per group, largest n first.
- `groupsSuppressed` (integer): Returned groups that are suppressed.
- `metric` (string): The metric computed.
- `multiValuedDimensions` (array): Dimensions where one case can sit in several groups, so group counts overlap.
- `names` (object): Names of the judges and firms in the groups.
- `totalGroups` (integer): Groups before the cap on how many are returned.
- `truncated` (boolean): True when more groups exist than were returned.
- `unit` (string): What the metric counts: cases, or motion rulings for motion_grant_rate.

### `search_judges` (~128 tokens)

Search judges

List judges by name and district, with case counts, most cases first. get_judge gives one judge in full.

Input parameters:

- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `district` (string): Judicial district, e.g. HARTFORD JD.
- `limit` (integer): Results per page, at most 50 (the default).
- `name` (string): Part of the name, any case.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

Output parameters:

- `nextCursor`: Pass as cursor for the next page; null on the last.
- `results` (array): This page of matches.
- `total` (integer): Matches across all pages.

### `get_judge` (~81 tokens)

Judge profile

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.

Input parameters:

- `judge_key` (string, required): Judge key from search_judges.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

### `search_firms` (~177 tokens)

Search law firms

List law firms by name, side, district and size, most cases first. get_firm gives one firm in full.

Input parameters:

- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `district` (string): Judicial district, e.g. HARTFORD JD.
- `limit` (integer): Results per page, at most 50 (the default).
- `min_cases` (integer): At least this many cases; with side, cases on that side.
- `name` (string): Part of the name, any case.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.
- `side` (string): Only those with cases for this side, ranked by their cases on that side rather than by all their cases.

Output parameters:

- `nextCursor`: Pass as cursor for the next page; null on the last.
- `results` (array): This page of matches.
- `total` (integer): Matches across all pages.

### `get_firm` (~163 tokens)

Law firm profile

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. A firm's case counts (cases, plaintiffCases, defenseCases) cover every case it appeared in. Its other figures (casesByYear, opposing firms, experts, motion practice, outcomes), the stats plaintiff_firm and defense_firm dimensions and the firm_juris_number filter cover only the cases where it is a side's lead firm, so one firm's case total can differ slightly from place to place.

Input parameters:

- `juris_number` (string, required): Firm juris number from search_firms.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

### `search_attorneys` (~171 tokens)

Search attorneys

List attorneys by name, firm, side and district, most cases first. get_attorney gives one attorney in full.

Input parameters:

- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `district` (string): Judicial district, e.g. HARTFORD JD.
- `firm_juris_number` (string): Juris number of their firm.
- `limit` (integer): Results per page, at most 50 (the default).
- `name` (string): Part of the name, any case.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.
- `side` (string): Only those with cases for this side, ranked by their cases on that side rather than by all their cases.

Output parameters:

- `nextCursor`: Pass as cursor for the next page; null on the last.
- `results` (array): This page of matches.
- `total` (integer): Matches across all pages.

### `get_attorney` (~100 tokens)

Attorney profile

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. An attorney's figures span every firm the attorney has filed with, not only their current firm.

Input parameters:

- `juris_number` (string, required): Attorney juris number from search_attorneys.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

### `search_providers` (~210 tokens)

Search medical providers

List 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.

Input parameters:

- `cursor` (string): nextCursor from the previous page; omit for the first page.
- `limit` (integer): Results per page, at most 50 (the default).
- `min_cases` (integer): At least this many cases.
- `name` (string): Part of the name, any case.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.
- `side` (string): treating: named as the plaintiff's treating provider; defense_examiner: retained by the defense to examine the plaintiff.
- `specialty` (string): Part of the specialty, e.g. orthop.
- `town` (string): Town the provider practises in.
- `type` (string): physician, therapy, imaging or facility.

Output parameters:

- `nextCursor`: Pass as cursor for the next page; null on the last.
- `results` (array): This page of matches.
- `total` (integer): Matches across all pages.

### `get_provider` (~90 tokens)

Medical provider profile

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 and on which body regions (counts only).

Input parameters:

- `provider_id` (string, required): Provider id from search_providers.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

### `request_data` (~88 tokens)

Request data

Tell 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.

Input parameters:

- `description` (string, required): What data you need and what you would use it for.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

Output parameters:

- `message` (string): Acknowledgement to pass on to the user.
- `received` (boolean): The submission was recorded.

### `send_message` (~121 tokens)

Send a 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 limits. Include the user's name or email only with their explicit permission.

Input parameters:

- `email` (string): The user's email, if they agreed and want a reply.
- `message` (string, required): The message.
- `name` (string): The user's name, if they agreed.
- `purpose` (string): One sentence on what you are trying to find out. Logged to improve the dataset; never returned.

Output parameters:

- `message` (string): Acknowledgement to pass on to the user.
- `received` (boolean): The submission was recorded.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 67
- 2026-11-03: 67
- 2026-11-02: 66
- 2026-11-01: 66
- 2026-10-31: 65
- 2026-10-30: 65

## Common questions

### What is the CT Injury Cases MCP server?

CT Injury Cases is an MCP server listed in the public MCP registry as com.ctinjurycases/ct-injury-cases. Connecticut personal injury litigation data: car accident cases, Hartford Judicial District. This page covers its hosted endpoint (https://ctinjurycases.com/mcp).

### Is the CT Injury Cases MCP server safe to use?

CT Injury Cases scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CT Injury Cases MCP server expose?

CT Injury Cases exposes 14 tools: describe_dataset, search_cases, get_case, stats, search_judges, and 9 more. Their descriptions and schemas cost roughly 2,238 tokens of context every time the server is loaded.

### Does the CT Injury Cases MCP server require authentication?

No. We connected to CT Injury Cases without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the CT Injury Cases MCP server still maintained?

CT Injury Cases is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://ctinjurycases.com/mcp
- Website: https://ctinjurycases.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases.json
- HTML version of this page: https://verifymcp.io/servers/com-ctinjurycases-ct-injury-cases/ctinjurycases