General Tools
stealpage.com
Provides general-purpose tools through the Model Context Protocol.
ENDPOINT 1
https://stealpage.com/api/mcp
MCP server metadata
- Name
- stealpage
- Version
- 1.0.0
STEALPAGE is an index of what companies publish — blogs, docs, pricing pages, changelogs, landing pages — converted to clean markdown and scored on what each page actually is. Use it whenever a question turns on what a specific company says, how an industry writes about something, or where a claim originates: reading the indexed text beats recalling it, and beats fetching a page that may be behind a bot wall. Start with search_content. Reach for list_content when the question is about a CATEGORY of writing rather than a subject ('technical posts with code', 'pricing pages that changed this year'). Two things to read carefully. `coverage.headline` on a company says how much of the site we actually have — a finished crawl is not a complete one. And `inlinks_body` counts citations from the BODY of other pages with template links excluded; plain `inlinks` would rank /login top on every site on the web, so never quote it as popularity.
Known tools 7
search_contentSearch everything companies publish, by meaning and by words at once.
Potential side effectslist_contentBrowse pages by their PROPERTIES rather than by a query — 'technical articles with code from developer-tool companies', 'pricing pages changed this year', 'the most-cited posts on this domain'.
Inferred read-onlylist_collectionsStart here when the question is about a CATEGORY of company rather than a named one — "the docs of the major payment APIs", "what shipped across AI providers this week".
Potential side effectsget_pageThe full cleaned markdown of one page, plus what we scored about it, its images with their alt text, every crawl we have of it, and which of the company's own pages cite it and under what wording.
Inferred read-onlyget_domainWhat a company publishes, in what languages, how much of it we have, and what moved recently.
Inferred read-onlyjob_statusProgress on a crawl: indexed, pending, discovered, elapsed, pages per minute and an eta.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.stealpage]
url = "https://stealpage.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"stealpage": {
"type": "http",
"url": "https://stealpage.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: stealpage
Remote MCP URL: https://stealpage.com/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"stealpage": {
"url": "https://stealpage.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"stealpage": {
"type": "http",
"url": "https://stealpage.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "stealpage",
"transport": "streamable-http",
"url": "https://stealpage.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.