# Redra (remote · mcp.redra.ai)

Search current class-action settlements and identify possible matches using structured filters.

- Trust score: 70/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.redra.ai`: 70/100 (this document), [markdown](https://verifymcp.io/servers/sacrosaunt-redra/mcp.md), [page](https://verifymcp.io/servers/sacrosaunt-redra/mcp)

## Channel facts

- Endpoint: `https://mcp.redra.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-08-03.

- **Endpoint Security**: 74/100
  - 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 is enforced; there's no plaintext access path.
  - 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**: 56/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2301 tokens (~460/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http sacrosaunt-redra https://mcp.redra.ai/mcp
```

### Codex

```toml
[mcp_servers.sacrosaunt-redra]
url = "https://mcp.redra.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sacrosaunt-redra": {
      "type": "remote",
      "url": "https://mcp.redra.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sacrosaunt-redra --url https://mcp.redra.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sacrosaunt-redra:
    url: "https://mcp.redra.ai/mcp"
```

### Other

```json
{
  "mcpServers": {
    "sacrosaunt-redra": {
      "type": "http",
      "url": "https://mcp.redra.ai/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.

### 2026-08-03 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 68, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 65, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 64, +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.

### 2026-07-27 (score 63, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (5)

### `search_settlements` (~498 tokens)

Search settlements

Search settlement records by keywords and structured filters.

        Every keyword is required: the list uses logical AND, not OR. Use separate
        searches for unrelated companies, products, or alternative terms. Keywords
        should describe companies, products, services, employers, incidents, or
        notices. For a broad eligibility scan, think expansively using relevant
        context and memory available to the agent and make multiple queries across
        plausible brands, aliases, parent companies, subsidiaries, purchases,
        providers, fees, incidents, and eligibility-relevant demographic angles such
        as age group, occupation, student or veteran status, parent or guardian status,
        and housing or household situation. Use the state filter for location. Do not
        invent user facts; speculative associations are search candidates only. Status is the
        claim lifecycle and defaults to open. Use all only for an intentional search
        across non-open lifecycle states too. Use settlement_type, not keywords, when
        the term describes the type of settlement rather than a specific entity or event.
        Source confidence is returned as objective metadata and quality flags; do not
        exclude possible matches using the provider's verification tier. Do not send
        names, addresses, account numbers, health details, or other identifying data.
        State is a two-letter US postal abbreviation.

Input parameters:

- `deadline_after`: Include deadlines on or after this ISO 8601 date.
- `deadline_before`: Include deadlines on or before this ISO 8601 date.
- `keywords`: Required AND terms for specific companies, brands, products, employers, or incidents. Do not put a settlement-type label here when settlement_type applies. For broad eligibility scans, make multiple…
- `limit` (integer): Maximum records returned, from 1 to 50.
- `proof_required`: Exact proof requirement: yes, no, optional, or unknown.
- `settlement_type`: Exact settlement taxonomy filter. Prefer this over keywords for type concepts such as data breaches, privacy, refunds, financial fees, or consumer products.
- `state`: Optional two-letter US postal abbreviation, such as CA.
- `status` (string): Claim lifecycle: open, closed, payment, unknown, or all. Defaults to open. Use all only when intentionally including non-open lifecycle states.

### `search_settlements_batch` (~256 tokens)

Search settlements in a batch

Run multiple independent settlement searches in one tool call.

        Prefer this tool for broad eligibility scans and alternative terms. Each
        query is evaluated independently. Returned records are deduplicated across
        queries and include matched_query_indices that point to the query summaries.
        Do not combine unrelated alternatives in one keywords list: keywords within
        each query use logical AND, never OR. Speculative associations are search
        candidates only, not evidence that the user matches a settlement. Choose
        per-query limits based on expected noise and use max_total_results to bound
        the unique records placed in model context without reducing search breadth.
        For current eligibility scans, omit status or set it to open; do not use all
        merely to broaden recall. The response's executed_query_count is the number
        of independent searches performed in this call.

Input parameters:

- `max_total_results` (integer): Maximum unique settlement records returned across the whole batch after cross-query deduplication. This caps output, not the number of independent searches performed.
- `queries` (array, required): Independent settlement searches. Use one query object per unrelated company, product, alias, alternative term, or search angle. Keywords inside each object still use logical AND.

### `get_settlement` (~120 tokens)

Get a settlement

Return one settlement and its official source links.

        When web access is available, use the official links to verify the complete
        class definition and eligibility terms before presenting the record as more
        than a possible match. Present plausible matches as concise lead cards that
        separate confirmed terms, relevant user context, and facts still needed.
        If browsing is unavailable, say the terms could not be independently checked,
        avoid guessing, and direct the user to the official link.

Input parameters:

- `settlement_id` (string, required): Exact settlement identifier returned by a search.

### `get_settlements` (~106 tokens)

Get settlements

Return complete stored records for multiple settlement finalists.

        Retrieve every finalist before presenting it. Use the records and official
        links to separate evidence-backed leads from plausible or speculative leads.
        A detail record does not itself prove that the user is eligible. If browsing
        is available, verify the complete class definition on the official source.

Input parameters:

- `settlement_ids` (array, required): Settlement identifiers to retrieve together. Use this for every finalist from a broad scan before composing the final answer.

### `get_dataset_info` (~23 tokens)

Get dataset information

Return source, license, freshness, counts, and hosted aggregate metrics.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sacrosaunt-redra/mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 69
- 2026-07-31: 68
- 2026-07-30: 65
- 2026-07-29: 65
- 2026-07-28: 64
- 2026-07-27: 63
- 2026-07-26: 63

## Links

- Remote endpoint: https://mcp.redra.ai/mcp
- Repository: https://github.com/sacrosaunt/Redra
- Website: https://redra.ai/
- Changelog RSS feed: https://verifymcp.io/servers/sacrosaunt-redra/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sacrosaunt-redra/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sacrosaunt-redra/mcp