The status403 site as MCP tools: services, technical write-ups, and any page as markdown.
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.
Answer the questions clients ask status403 before booking — what the discovery call covers, how feasibility is assessed, what to prepare, whether delivery is production-ready or prototype, blocked and protected targets, and post-launch support. Also returns how a project runs, from first call to handoff. Pass a query to narrow it to the relevant answers.
Optional keyword, such as "support" or "feasibility". Omit for everything.
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://status403.com/mcp
Answer the questions clients ask status403 before booking — what the discovery call covers, how feasibility is assessed, what to prepare, whether delivery is production-ready or prototype, blocked and protected targets, and post-launch support. Also returns how a project runs, from first call to handoff. Pass a query to narrow it to the relevant answers.
| Argument | Type | Description |
|---|---|---|
| query | string | Optional keyword, such as "support" or "feasibility". Omit for everything. |
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional keyword, such as \"support\" or \"feasibility\". Omit for everything."
}
},
"additionalProperties": false
}List the engineering services status403 offers — web scraping, reverse engineering, web3 and dApp engineering, and backend, frontend, and infrastructure engineering for new builds or existing systems — with what each one covers and the anchor link to its section on the page. Pass a query to keep only the services matching a keyword such as "scraping" or "anti-bot".
| Argument | Type | Description |
|---|---|---|
| query | string | Optional keyword to filter by. Omit to list every service. |
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional keyword to filter by. Omit to list every service."
}
},
"additionalProperties": false
}Read any page of status403 as markdown: "/" for the homepage (services, process, booking, FAQ), "/blog" for the post index, or "/blog/<slug>" for a post in full. This is the same document the site serves to clients that ask for it with `Accept: text/markdown`.
| Argument | Type | Description |
|---|---|---|
| path* | string | Site path, such as "/" or "/blog/<slug>". A full status403.com URL works too. |
{
"type": "object",
"required": [
"path"
],
"properties": {
"path": {
"type": "string",
"description": "Site path, such as \"/\" or \"/blog/<slug>\". A full status403.com URL works too."
}
},
"additionalProperties": false
}Search the status403 technical write-ups on antibot systems, TLS fingerprinting, reverse engineering, scraping, and automation architecture. Returns matching posts with their title, date, tags, excerpt, and URL — pass a returned path to read_page for the full text. Omit the query to get the most recent posts.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many posts to return, most relevant first. |
| query | string | Words to search for in titles, tags, excerpts, and post bodies. |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 5,
"maximum": 20,
"minimum": 1,
"description": "How many posts to return, most relevant first."
},
"query": {
"type": "string",
"description": "Words to search for in titles, tags, excerpts, and post bodies."
}
},
"additionalProperties": false
}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 18, 2026.