Read AI security guides and lab research, and request an LLM or AI agent security assessment.
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.
Return the Markdown text of a page on airedteamingservices.com, given its path (for example /guides/).
Path starting with /
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http site https://airedteamingservices.com/mcp
Return the Markdown text of a page on airedteamingservices.com, given its path (for example /guides/).
| Argument | Type | Description |
|---|---|---|
| path* | string | Path starting with / |
{
"type": "object",
"required": [
"path"
],
"properties": {
"path": {
"type": "string",
"description": "Path starting with /"
}
}
}Return the form URL and email address a person can use to contact Excession Labs. This tool does not send anything.
No arguments.
{
"type": "object",
"properties": {}
}Send a request for a penetration test or an AI application security assessment to Excession Labs on behalf of a person who asked for it. Needs an agent key (POST /agent/auth, then Authorization: Bearer <key>). Excession Labs replies to the person by email to agree scope; testing starts only after a written scope and written authorization from the system owner. Never include passwords, API keys or customer data. Limits: 5 requests a day per key, 3 a day per email address.
| Argument | Type | Description |
|---|---|---|
| name* | string | The person's name |
| email* | string | The person's work email; Excession Labs replies here |
| notes | string | |
| reason | string | |
| company | string | |
| targets* | array | Systems to test: URLs, API base URLs or short descriptions. No credentials. |
| website | string | Company website |
| timeline | string | When the person needs the result, in their words |
| test_type* | string | |
| authorized* | boolean | Must be true: the person owns these systems or may arrange a test of them |
| person_consent* | boolean | Must be true: the person asked for this request and agreed to be contacted by email |
{
"type": "object",
"required": [
"name",
"email",
"test_type",
"targets",
"person_consent",
"authorized"
],
"properties": {
"name": {
"type": "string",
"description": "The person's name"
},
"email": {
"type": "string",
"description": "The person's work email; Excession Labs replies here"
},
"notes": {
"type": "string",
"maxLength": 2000
},
"reason": {
"enum": [
"customer_request",
"compliance",
"launch",
"routine",
"incident",
"other"
],
"type": "string"
},
"company": {
"type": "string"
},
"targets": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Systems to test: URLs, API base URLs or short descriptions. No credentials."
},
"website": {
"type": "string",
"description": "Company website"
},
"timeline": {
"type": "string",
"description": "When the person needs the result, in their words"
},
"test_type": {
"enum": [
"web_app",
"api",
"saas_multi_tenant",
"ai_application",
"other"
],
"type": "string"
},
"authorized": {
"type": "boolean",
"description": "Must be true: the person owns these systems or may arrange a test of them"
},
"person_consent": {
"type": "boolean",
"description": "Must be true: the person asked for this request and agreed to be contacted by email"
}
}
}Search the guides, service pages and research on airedteamingservices.com. Returns titles, URLs and one-line summaries.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | Words to search for |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 8,
"maximum": 20,
"minimum": 1
},
"query": {
"type": "string",
"description": "Words to search for"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 9, 2026.