PDF Slim — PDF Compression for AI is an MCP server with 3 tools an agent can call, among them compress_pdf, inspect_pdf, optimize_pdf. It answers at https://api.pdfslim.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Compress PDFs to exact target sizes (82-93% smaller). Tools: compress_pdf, optimize_pdf, inspect_pdf
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
compress_pdf | Compress a PDF file to reduce its size. Renders pages and re-encodes as JPEG, iterating quality/resolution to hit a target size. Use this when a user wants to shrink a PDF (e.g. to 500KB, 1MB, or "smaller"). Free anonymous tier: 20 calls/da Inputs: file_base64, target_size, quality |
inspect_pdf | Inspect a PDF: page count, file size, password protection. Use before deciding how to process a PDF. Free anonymous tier: 20 calls/day per IP. More calls need an API key (https://ko-fi.com/yugutou/shop). Inputs: file_base64 |
optimize_pdf | Lossless PDF optimization: garbage collection, stream re-compression. No quality loss. Good for PDFs with redundant data; effect is small on already-optimized files. Free anonymous tier: 20 calls/day per IP, files up to 10MB. Larger files / Inputs: file_base64 |
Every block below points at https://api.pdfslim.app/mcp. Pick your client and copy.
claude mcp add --transport http pdf-slim-pdf-compression-for-ai https://api.pdfslim.app/mcp
{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.pdfslim.app/mcp"]
}
}
}{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"url": "https://api.pdfslim.app/mcp"
}
}
}{
"servers": {
"pdf-slim-pdf-compression-for-ai": {
"type": "http",
"url": "https://api.pdfslim.app/mcp"
}
}
}{
"context_servers": {
"pdf-slim-pdf-compression-for-ai": {
"url": "https://api.pdfslim.app/mcp"
}
}
}{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"serverUrl": "https://api.pdfslim.app/mcp"
}
}
}{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"url": "https://api.pdfslim.app/mcp"
}
}
}name: PDF Slim — PDF Compression for AI
version: 0.0.1
schema: v1
mcpServers:
- name: PDF Slim — PDF Compression for AI
type: streamable-http
url: https://api.pdfslim.app/mcp{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"httpUrl": "https://api.pdfslim.app/mcp"
}
}
}{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"type": "http",
"url": "https://api.pdfslim.app/mcp"
}
}
}{
"mcpServers": {
"pdf-slim-pdf-compression-for-ai": {
"url": "https://api.pdfslim.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.pdfslim.app%2Fmcp&type=streamable_http&id=pdf-slim-pdf-compression-for-ai&name=PDF%20Slim%20%E2%80%94%20PDF%20Compression%20for%20AI
It answered our last check on 24 October 2026 in 250 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
3, as returned by the server's own tools/list on 22 September 2026: compress_pdf, inspect_pdf, optimize_pdf.
It answered our last check on 24 October 2026 in 250 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.pdfslim.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.zhaoyaqi18. Endpoint host: api.pdfslim.app. ARD identifier: urn:air:io.github.zhaoyaqi18:mcp:pdfslim.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.