PDF MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 1 901 installs a week from pypi. Last commit 17 Sep 2026.
Agentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.
We read the source, 18 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
pdf = os.path.join(CORPUS, f"{arxiv_id}.pdf")
child = spawn(cmd, args, { ...opts, windowsHide: true });
result = subprocess.run(
document.getElementById("clientNote").innerHTML = c.note;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add pdf-mcp -- uvx pdf-mcp
{
"mcpServers": {
"pdf-mcp": {
"args": [
"pdf-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.pdf-mcp]
command = "uvx"
args = ["pdf-mcp"]
{
"mcpServers": {
"pdf-mcp": {
"args": [
"pdf-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"pdf-mcp": {
"args": [
"pdf-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
PDF_MCP_CACHE_DIR (Directory for storing PDF cache (default: ~/.cache/pdf-mcp)), PDF_MCP_CACHE_TTL (Cache time-to-live in hours (default: 24)).
The author declared them in the registry entry; get the values from the project itself.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Free open-source web search and page reading for LLMs, AI agents, and RAG.
Similarity search, hybrid search, and index management for pgvector-backed PostgreSQL tables
Semantic code search for AI agents — hybrid BM25+vector, call-graph, 20+ languages.
Bounded KVP, RAG search, and wipe receipts for agent jobs over remote MCP
Managed Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers
Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Answers built from our own checks of this server.