Check whether a website works for AI agents before visiting it, and the steps that worked.
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.
Look up how well an AI agent could use a website when Botworthy last scanned it: whether it blocked agents, the score out of 100, advice, and for each of 5 everyday tasks the outcome and the exact steps (control role and accessible name) that worked. Accepts any URL or domain. If the site hasn't been scanned, says whether a scan is queued.
A URL or domain, e.g. https://www.example.com/shop or example.com
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http botworthy https://botworthy.dev/mcp
Look up how well an AI agent could use a website when Botworthy last scanned it: whether it blocked agents, the score out of 100, advice, and for each of 5 everyday tasks the outcome and the exact steps (control role and accessible name) that worked. Accepts any URL or domain. If the site hasn't been scanned, says whether a scan is queued.
| Argument | Type | Description |
|---|---|---|
| site* | string | A URL or domain, e.g. https://www.example.com/shop or example.com |
{
"type": "object",
"required": [
"site"
],
"properties": {
"site": {
"type": "string",
"description": "A URL or domain, e.g. https://www.example.com/shop or example.com"
}
}
}Tell Botworthy how one of its 5 tasks went when you did it on a website. Reports aren't published: they decide what gets scanned or rescanned next. Only send it for visits where you didn't log in, didn't enter personal data, and didn't get around a CAPTCHA or bot check, and never include anything about the user.
| Argument | Type | Description |
|---|---|---|
| site* | string | A URL or domain |
| task* | string | find-pricing: Find a price; search: Search for something; start-checkout: Start a purchase or sign-up; find-support: Find a human; find-policy: Find the fine print |
| agent | string | Your agent's name, optional |
| steps* | array | The actions you took, in order |
| reason | string | One line on what happened |
| outcome* | string | |
| ranFrom | string | Where your browser ran |
| finalUrl | string | |
| followedRules* | object | All three must be true, or the report is turned away |
{
"type": "object",
"required": [
"site",
"task",
"outcome",
"steps",
"followedRules"
],
"properties": {
"site": {
"type": "string",
"description": "A URL or domain"
},
"task": {
"enum": [
"find-pricing",
"search",
"start-checkout",
"find-support",
"find-policy"
],
"type": "string",
"description": "find-pricing: Find a price; search: Search for something; start-checkout: Start a purchase or sign-up; find-support: Find a human; find-policy: Find the fine print"
},
"agent": {
"type": "string",
"description": "Your agent's name, optional"
},
"steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"action"
],
"properties": {
"ok": {
"type": "boolean",
"description": "false if the step didn't work"
},
"url": {
"type": "string",
"description": "Page URL after the step"
},
"name": {
"type": "string",
"description": "Accessible name of the control"
},
"role": {
"type": "string",
"description": "ARIA role of the control, e.g. link or button"
},
"value": {
"type": "string",
"description": "Text typed. Search queries only"
},
"action": {
"enum": [
"open",
"goto",
"click",
"type",
"press",
"scroll",
"back",
"find",
"wait",
"other"
],
"type": "string"
}
}
},
"maxItems": 40,
"description": "The actions you took, in order"
},
"reason": {
"type": "string",
"description": "One line on what happened"
},
"outcome": {
"enum": [
"success",
"partial",
"failed",
"blocked"
],
"type": "string"
},
"ranFrom": {
"enum": [
"cloud",
"user_browser",
"unknown"
],
"type": "string",
"description": "Where your browser ran"
},
"finalUrl": {
"type": "string"
},
"followedRules": {
"type": "object",
"required": [
"noLogin",
"noPersonalData",
"noBotCheckBypass"
],
"properties": {
"noLogin": {
"type": "boolean",
"description": "Didn't log in or create an account"
},
"noPersonalData": {
"type": "boolean",
"description": "Didn't enter personal data (a search query is fine)"
},
"noBotCheckBypass": {
"type": "boolean",
"description": "Didn't solve or get around a CAPTCHA or bot check"
}
},
"description": "All three must be true, or the report is turned away"
}
}
}Queue a website that Botworthy hasn't scanned yet. Scans run in batches by Botworthy's own agent, so expect days, not minutes; don't wait for it. Sites already scanned aren't queued again.
| Argument | Type | Description |
|---|---|---|
| note | string | Optional, up to 300 characters |
| site* | string | A URL or domain |
| agent | string | Your agent's name, optional |
{
"type": "object",
"required": [
"site"
],
"properties": {
"note": {
"type": "string",
"description": "Optional, up to 300 characters"
},
"site": {
"type": "string",
"description": "A URL or domain"
},
"agent": {
"type": "string",
"description": "Your agent's name, optional"
}
}
}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 6, 2026.