Find real software, security and AI-agent failures that resemble your design, with safeguards.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh 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.
Two to five sentences: what the system does, what it can change, what data it reads, which services it calls.
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.
| Argument | Type | Description |
|---|---|---|
| proposal* | string | Two to five sentences: what the system does, what it can change, what data it reads, which services it calls. |
| max_results | integer |
{
"type": "object",
"required": [
"proposal"
],
"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",
"default": 5,
"maximum": 10,
"minimum": 1
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| files | array | Relevant text files. Description plus file contents must fit within 25,000 characters and the 32 KB request limit. Remove credentials and personal data. |
| proposal | string | Observed app behavior, integrations, data flows, permissions and deployment context. Optional when files are supplied. |
| max_results | integer | |
| repository_url | string | Public GitHub repository home URL, e.g. https://github.com/owner/app. Imports a small selection of docs, config and source at one commit. |
{
"type": "object",
"anyOf": [
{
"required": [
"proposal"
]
},
{
"required": [
"files"
]
},
{
"required": [
"repository_url"
]
}
],
"properties": {
"files": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"content"
],
"properties": {
"name": {
"type": "string",
"maxLength": 160
},
"content": {
"type": "string",
"maxLength": 25000
}
}
},
"maxItems": 10,
"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."
},
"proposal": {
"type": "string",
"maxLength": 25000,
"description": "Observed app behavior, integrations, data flows, permissions and deployment context. Optional when files are supplied."
},
"max_results": {
"type": "integer",
"default": 5,
"maximum": 10,
"minimum": 1
},
"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."
}
}
}Full record for one incident by ID (e.g. SEA-POST-005): what happened, source, failure pattern, safeguards and review status.
| Argument | Type | Description |
|---|---|---|
| id* | string |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| mode | string | |
| format | string | |
| proposal* | string |
{
"type": "object",
"required": [
"proposal"
],
"properties": {
"mode": {
"enum": [
"design",
"existing_app"
],
"type": "string",
"default": "design"
},
"format": {
"enum": [
"agents",
"claude",
"cursor",
"copilot"
],
"type": "string",
"default": "agents"
},
"proposal": {
"type": "string"
}
}
}The 14 recurring failure patterns with triggers, warning signs and engineering principles.
No arguments.
{
"type": "object",
"properties": {}
}Keyword search over documented incidents and security advisories (company, technology, CVE, failure mode). Returns titles, summaries, evidence labels and URLs.
| Argument | Type | Description |
|---|---|---|
| query* | string | e.g. "idempotency", "Redis tenant", "prompt injection", "CVE-2021-44228" |
| cursor | string | Pagination cursor from a previous call |
| max_results | integer | |
| include_advisories | boolean |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "e.g. \"idempotency\", \"Redis tenant\", \"prompt injection\", \"CVE-2021-44228\""
},
"cursor": {
"type": "string",
"description": "Pagination cursor from a previous call"
},
"max_results": {
"type": "integer",
"default": 8,
"maximum": 25,
"minimum": 1
},
"include_advisories": {
"type": "boolean",
"default": true
}
}
}