ENDPOINT 1
https://api.preteworks.com/mcp
MCP server metadata
- Name
- preteworks
- Version
- 1.1.0
Known tools 15
extract_pdf_textExtract the text content of a PDF — for RAG, summarization, or search.
Inferred read-onlysplit_pdfSplit a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'.
Inferred read-onlyfill_pdf_formFill a PDF's form fields from a map of field -> value; optionally flatten.
Inferred read-onlyread_urlFetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG.
Inferred read-onlyscrape_pageFetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render.
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.preteworks]
url = "https://api.preteworks.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"preteworks": {
"type": "http",
"url": "https://api.preteworks.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: preteworks
Remote MCP URL: https://api.preteworks.com/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": {
"preteworks": {
"url": "https://api.preteworks.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"preteworks": {
"type": "http",
"url": "https://api.preteworks.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "preteworks",
"transport": "streamable-http",
"url": "https://api.preteworks.com/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.