Skip to content

CollectSEA

by kelvin-ling · remote · no sign-in to list tools · v2026.10.17 · published by GitHub user kelvin-ling

Find real software, security and AI-agent failures that resemble your design, with safeguards.

Read only
CompareRegistry entry

6 tools: 6 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http collectsea https://collectsea.com/mcp

Findings

Matches of fixed checks, with the text they matched.

1 info
  • Infoanalyze_existing_app

    The input schema at properties.files.description mentions "credentials".

    Matched text

    inputSchema.properties.files.description: "...ers and the 32 KB request limit. Remove credentials and personal data."

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Only reads 6Claude Code: allow
  • analyze_designProfile a proposed feature, system or AI-agent workflow and return documented incidents from systems that behaved similarly, their failure patterns, and the safeguards to build in.No findings

    Why it is in this group

    • The name "analyze_design" says "analyze": a word for reading.
    Description, as the server wrote it
    Profile a proposed feature, system or AI-agent workflow and return documented incidents from systems that behaved similarly, their failure patterns, and the safeguards to build in. Use before writing code for anything that moves money, deletes data, changes permissions, runs code, or acts on external content.

    Annotations the server declares

    • title: Find failure precedents for a design
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • analyze_existing_appAnalyze an existing app using observed behavior, README, architecture notes, configuration or source snippets.1 finding

    Why it is in this group

    • The name "analyze_existing_app" says "analyze": a word for reading.

    Findings

    • Info

      The input schema at properties.files.description mentions "credentials".

      Matched text

      inputSchema.properties.files.description: "...ers and the 32 KB request limit. Remove credentials and personal data."

      What this check looks for
    Description, as the server wrote it
    Analyze an existing app using observed behavior, README, architecture notes, configuration or source snippets. Provide a public GitHub repository_url to import selected context, or inspect a private repository locally and submit relevant text. Code is never executed and the running app is not scanned. Returns source context, behavior signals, historical precedents and safeguards to verify.

    Annotations the server declares

    • title: Find failure precedents for an existing app
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_incidentFull record for one incident by ID (e.g.No findings

    Why it is in this group

    • The name "get_incident" says "get": a word for reading.
    Description, as the server wrote it
    Full record for one incident by ID (e.g. SEA-POST-005): what happened, source, failure pattern, safeguards and review status.

    Annotations the server declares

    • title: Get one incident record
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_safeguardsReturn ready-to-save rules (AGENTS.md by default; also CLAUDE.md, Cursor rule or Copilot instructions) for a proposed design, each rule citing the incidents behind it.No findings

    Why it is in this group

    • The name "get_safeguards" says "get": a word for reading.
    Description, as the server wrote it
    Return ready-to-save rules (AGENTS.md by default; also CLAUDE.md, Cursor rule or Copilot instructions) for a proposed design, each rule citing the incidents behind it.

    Annotations the server declares

    • title: Get agent rules for a design
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_failure_patternsThe 14 recurring failure patterns with triggers, warning signs and engineering principles.No findings

    Why it is in this group

    • The name "list_failure_patterns" says "list": a word for reading.
    Description, as the server wrote it
    The 14 recurring failure patterns with triggers, warning signs and engineering principles.

    Annotations the server declares

    • title: List failure patterns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_incidentsKeyword search over documented incidents and security advisories (company, technology, CVE, failure mode).No findings

    Why it is in this group

    • The name "search_incidents" says "search": a word for reading.
    Description, as the server wrote it
    Keyword search over documented incidents and security advisories (company, technology, CVE, failure mode). Returns titles, summaries, evidence labels and URLs.

    Annotations the server declares

    • title: Search the incident database
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 2026.10.17. Values in angle brackets are yours to fill in.

claude mcp add --transport http collectsea https://collectsea.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__collectsea__analyze_design",
      "mcp__collectsea__analyze_existing_app",
      "mcp__collectsea__search_incidents",
      "mcp__collectsea__get_incident",
      "mcp__collectsea__list_failure_patterns",
      "mcp__collectsea__get_safeguards"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as collectsea. Review it before you use it.