Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/xxx87/pdf-to-text-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/xxx87/pdf-to-text-mcp/pdf-to-text-mcp-server)<a href="https://agentmods.dev/mcp/xxx87/pdf-to-text-mcp/pdf-to-text-mcp-server"><img src="https://agentmods.dev/badge/mcp/xxx87/pdf-to-text-mcp/pdf-to-text-mcp-server/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/xxx87/pdf-to-text-mcp/pdf-to-text-mcp-server"><img src="https://agentmods.dev/badge/mcp/xxx87/pdf-to-text-mcp/pdf-to-text-mcp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pdf-to-text-mcp-server scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "pdf-to-text-mcp-server": { "command": "npx", "args": [ "-y", "pdf-to-text-mcp-server" ] } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 9 lines scan A 298485c3d69c
pdf-to-text-mcp-server is an MCP server published in the GitHub repository xxx87/pdf-to-text-mcp (0 stars, last pushed 11mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
magicslides-mcp
Create presentations, docs, sheets and meeting notes from chat. Hosted link, editor, PPTX & PDF. Remote server at www.magicslides.app.
onepdf-mcp-server
97 trustworthy PDF tools for Claude, Cursor, Codex, and other MCP clients. Runs locally from the onepdf-mcp-server npm package.
pretext-pdf-mcp
MCP server: generate professional PDFs from JSON in Claude, Cursor, Windsurf, or any AI agent. Serverless, no Chromium. Invoices, reports, resumes. Runs locally from the pretext-pdf-mcp npm package.
mcp-pdf-utils
Local MCP server for PDF manipulation — merge, split, rotate, extract, watermark, metadata. Zero API keys, fully offline. Works with Claude, Cursor, ChatGPT. Runs locally from the mcp-pdf-utils npm package.
pdf-mcp
MCP server "pdf-mcp" as configured in I-CAN-hack/pdf-mcp. Runs locally from the src/pdf_mcp/server.py Python package.
pdf-reader-mcp
MCP server for PDF structure analysis - read, inspect, and validate PDF internals. Runs locally from the @shuji-bonji/pdf-reader-mcp npm package.