CollectSEA
Find real software, security and AI-agent failures that resemble your design, with safeguards.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"collectsea": {
"url": "https://collectsea.com/mcp"
}
}
}Remote-Endpunkte
https://collectsea.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (6)
🟢analyze_design(proposal, max_results)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"proposal": {
"type": "string",
"description": "Two to five sentences: what the system does, what it can change, what data it reads, which services it calls."
},
"max_results": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 5
}
},
"required": [
"proposal"
]
}🟢analyze_existing_app(repository_url, proposal, files, max_results)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"repository_url": {
"type": "string",
"description": "Public GitHub repository home URL, e.g. https://github.com/owner/app. Imports a small selection of docs, config and source at one commit."
},
"proposal": {
"type": "string",
"maxLength": 25000,
"description": "Observed app behavior, integrations, data flows, permissions and deployment context. Optional when files are supplied."
},
"files": {
"type": "array",
"maxItems": 10,
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"maxLength": 160
},
"content": {
"type": "string",
"maxLength": 25000
}
},
"required": [
"name",
"content"
]
},
"description": "Relevant text files. Description plus file contents must fit within 25,000 characters and the 32 KB request limit. Remove credentials and personal data."
},
"max_results": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"default": 5
}
},
"anyOf": [
{
"required": [
"proposal"
]
},
{
"required": [
"files"
]
},
{
"required": [
"repository_url"
]
}
]
}🟢search_incidents(query, max_results, include_advisories, cursor)
Keyword search over documented incidents and security advisories (company, technology, CVE, failure mode). Returns titles, summaries, evidence labels and URLs.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "e.g. \"idempotency\", \"Redis tenant\", \"prompt injection\", \"CVE-2021-44228\""
},
"max_results": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"default": 8
},
"include_advisories": {
"type": "boolean",
"default": true
},
"cursor": {
"type": "string",
"description": "Pagination cursor from a previous call"
}
},
"required": [
"query"
]
}🟢get_incident(id)
Full record for one incident by ID (e.g. SEA-POST-005): what happened, source, failure pattern, safeguards and review status.
Eingabe-Schema
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
]
}🟢list_failure_patterns
The 14 recurring failure patterns with triggers, warning signs and engineering principles.
Eingabe-Schema
{
"type": "object",
"properties": {}
}🟢get_safeguards(proposal, mode, format)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"proposal": {
"type": "string"
},
"mode": {
"type": "string",
"enum": [
"design",
"existing_app"
],
"default": "design"
},
"format": {
"type": "string",
"enum": [
"agents",
"claude",
"cursor",
"copilot"
],
"default": "agents"
}
},
"required": [
"proposal"
]
}Community
Nachweis