Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Redra

REMOTE · MCP.REDRA.AI · SCANNED SEP 20

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

Available components

0 this week 85 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Endpoint Security74
Transport & Reachability100
Schema Quality & AI Usability73
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 884 tokens (~176/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Redra MCP server?

Redra is a hosted endpoint at https://mcp.redra.ai/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.

remote · mcp.redra.ai

# add to Claude Code
claude mcp add --transport http sacrosaunt-redra 'https://mcp.redra.ai/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "sacrosaunt-redra": {
      "url": "https://mcp.redra.ai/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "sacrosaunt-redra": {
      "type": "http",
      "url": "https://mcp.redra.ai/mcp"
    }
  }
}
# ~/.codex/config.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
    }
  }
}
# add to OpenClaw
openclaw mcp add sacrosaunt-redra --url 'https://mcp.redra.ai/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  sacrosaunt-redra:
    url: "https://mcp.redra.ai/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "sacrosaunt-redra": {
      "Transport": "http",
      "Url": "https://mcp.redra.ai/mcp"
    }
  }
}
# add to Vellum
assistant mcp add sacrosaunt-redra -t streamable-http -u 'https://mcp.redra.ai/mcp'
// mcp.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 we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 26 Aug 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 24 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Aug 26 0
    • Tool “get_settlement” rewrote its description, which is the text the model reads security
    • Tool “get_settlements” rewrote its description, which is the text the model reads security
    • Tool “search_settlements” rewrote its description, which is the text the model reads security
    • Tool “search_settlements_batch” rewrote its description, which is the text the model reads security
    • “search_settlements” reworded the description of “proof_required” cosmetic
  • 13 Aug 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 1.29.0 → 0.1.0 functional
    • “search_settlements” reworded the description of “proof_required” cosmetic
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 7 Aug 26 0
    • The server no longer declares the “experimental” capability functional
  • 5 Aug 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “get_settlement” rewrote its description, which is the text the model reads security
    • Tool “get_settlements” rewrote its description, which is the text the model reads security
    • Tool “search_settlements” rewrote its description, which is the text the model reads security
    • Tool “search_settlements_batch” rewrote its description, which is the text the model reads security
    • Schema quality: 460 → 176 functional
    • Server version: 1.28.1 → 1.29.0 functional
    • “get_settlements” reworded the description of “settlement_ids” cosmetic
    • “search_settlements” reworded the description of “keywords” cosmetic
    • “search_settlements” reworded the description of “status” cosmetic
    • “search_settlements_batch” reworded the description of “queries” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://mcp.redra.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.redra.ai CN=YE2,O=Let's Encrypt,C=US 25 Jul 2026 23 Oct 2026 ECDSA 256 ECDSA-SHA384 6481171259a49f3c398d5ca2f17f665398f
SANs: mcp.redra.ai
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.redra.ai. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
redra.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.redra.ai/mcp Verified 200
http (plaintext) http://mcp.redra.ai/mcp HTTPS enforced 301 https://mcp.redra.ai/mcp
MCP tools · 5 exposed · ~458 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_dataset_info ~23

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_settlement ~42

Return the complete stored record and official source links for one settlement ID produced by a search.

NameTypeReqDescription
settlement_idstringyesExact settlement identifier returned by a search.

Structured output declared, but exposes no named fields.

No examples provided.

get_settlements ~45

Return complete stored records and official source links for up to 20 settlement IDs produced by search.

NameTypeReqDescription
settlement_idsarrayyesSettlement identifiers returned by search to retrieve together.

Structured output declared, but exposes no named fields.

No examples provided.

search_settlements ~231

Search one settlement angle using logical AND keywords and structured status, type, state, proof, and deadline filters. Status defaults to open. Results include source metadata and quality flags.

NameTypeReqDescription
deadline_afterInclude deadlines on or after this ISO 8601 date.
deadline_beforeInclude deadlines on or before this ISO 8601 date.
keywordsRequired logical-AND terms for specific companies, brands, products, employers, services, or incidents. Use separate queries for alternatives and settlement_type for taxonomy.
limitintegerMaximum records returned, from 1 to 50.
proof_requiredWhether proof is required: yes, no, or unknown.
settlement_typeExact settlement taxonomy filter. Prefer this over keywords for type concepts such as data breaches, privacy, refunds, financial fees, or consumer products.
stateOptional two-letter US postal abbreviation, such as CA.
statusstringPublic lifecycle filter: open or upcoming. Defaults to open. Upcoming records are not yet claimable and must be presented as a separate watchlist.

Structured output declared, but exposes no named fields.

No examples provided.

search_settlements_batch ~117

Run up to 50 independent settlement searches and deduplicate records across queries. Results include matched_query_indices, and executed_query_count reports the number of searches performed. Use when several unrelated search angles should be evaluated together.

NameTypeReqDescription
max_total_resultsintegerMaximum unique settlement records returned across the whole batch after cross-query deduplication. This caps output, not the number of independent searches performed.
queriesarrayyesIndependent settlement searches. Each query retains logical-AND keyword semantics; unrelated alternatives belong in separate query objects.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Redra MCP server?

Redra is an MCP server listed in the public MCP registry as io.github.sacrosaunt/redra. Search current class-action settlements and identify possible matches using structured filters. This page covers its hosted endpoint (https://mcp.redra.ai/mcp).

Is the Redra MCP server safe to use?

Redra scores 85 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 Redra MCP server expose?

Redra exposes 5 tools: search_settlements, search_settlements_batch, get_settlement, get_settlements, get_dataset_info. Their descriptions and schemas cost roughly 458 tokens of context every time the server is loaded.

Does the Redra MCP server require authentication?

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

Is the Redra MCP server still maintained?

Redra is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.