Skills/PyPI/pdfkb-mcp

pdfkb-mcp@0.7.0

VERIFIED· not started

Publisher claims: "A Model Context Protocol server for managing PDF documents with vector search capabilities" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher juanqui · publishing for 464 daysInstalls 95Last detonated 1 h ago
$claude mcp add pdfkb-mcp -- uvx pdfkb-mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
HF_TOKENOPENAI_API_KEYOPENROUTER_API_KEYPDFKB_DEEPINFRA_API_KEYPDFKB_HUGGINGFACE_API_KEYPDFKB_OPENAI_API_KEYPDFKB_OPENROUTER_API_KEYPDFKB_SUMMARIZER_API_KEYConfiguration, not credentials: CACHE_DIR, CHUNK_OVERLAP, CHUNK_SIZE, DOCLING_DEVICE, DOCLING_FORMULA_ENRICHMENT, DOCLING_MAX_PAGES, DOCLING_OCR_ENGINE, DOCLING_OCR_LANGUAGES, DOCLING_PROCESSING_TIMEOUT, DOCLING_TABLE_MODE, EMBEDDING_BATCH_SIZE, EMBEDDING_MODEL, FILE_SCAN_INTERVAL, KNOWLEDGEBASE_PATH, MARKER_LLM_MODEL, MARKER_USE_LLM, MINERU_LANG, MINERU_METHOD, MINERU_VRAM, PDF_CHUNKER, PDF_PARSER, PDF_PROCESSING_STRATEGY, PDFKB_BACKGROUND_QUEUE_WORKERS, PDFKB_CACHE_DIR, PDFKB_CHUNK_OVERLAP, PDFKB_CHUNK_SIZE, PDFKB_DEEPINFRA_RERANKER_MODEL, PDFKB_DOCLING_DEVICE, PDFKB_DOCLING_FORMULA_ENRICHMENT, PDFKB_DOCLING_MAX_PAGES, PDFKB_DOCLING_OCR_ENGINE, PDFKB_DOCLING_OCR_LANGUAGES
Where it talks to
no vendor host named in the codeAlso openrouter.ai, deepinfra.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names openrouter.ai, deepinfra.com as well as its own vendor. The guard injects HF_TOKEN, OPENAI_API_KEY, OPENROUTER_API_KEY, PDFKB_DEEPINFRA_API_KEY, PDFKB_HUGGINGFACE_API_KEY, PDFKB_OPENAI_API_KEY, PDFKB_OPENROUTER_API_KEY, PDFKB_SUMMARIZER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx pdfkb-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 83/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/pdfkb/config.py:359 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesAutomatically loads from .env file if it exists in the current directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/pdfkb/web_server.py:343 · MCP server using network transport (SSE/HTTP) — data sent over networkawait self.mcp_server.app.run_http_async(Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathssrc/pdfkb/config.py:368 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load .env file if it existsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/webui/components/FileUpload.js:32 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('FileUpload component initialized');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedsrc/pdfkb/parsers/parser_mineru.py:129 · Python subprocess execution detectedprocess = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathssrc/pdfkb/config.py:374 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespotential_env = path / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/pdfkb/config.py:372 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Look for .env file in current directory and parent directoriesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/pdfkb/parsers/parser_mineru.py:46 · Python subprocess execution detectedresult = subprocess.run(["mineru", "--version"], capture_output=True, text=True, timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈57 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for pdfkb-mcp@0.7.0 as of 55 min ago. This is the package itself, not its dependencies.

pdfkb-mcp@0.7.0 safety verdict: Verified (not started) — KillerSkills