Skills/PyPI/pdf-capture-mcp

pdf-capture-mcp@0.12.0

VERIFIED· not started

Publisher claims: "Multi-phase PDF capture pipeline as an MCP server. Convert PDF to high-quality structured Markdown." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher chenhongyu2026 · publishing for 111 daysInstalls 102Last detonated 1 h ago
$claude mcp add pdf-capture-mcp -- uvx pdf-capture-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
PDF_CAPTURE_EMBEDDING_API_KEYPDF_CAPTURE_VLM_API_KEYConfiguration, not credentials: HF_ENDPOINT, HF_HUB_DISABLE_XET, HF_HUB_OFFLINE, MINERU_MODEL_SOURCE, MINERU_PDF_RENDER_THREADS, OMP_NUM_THREADS, PDF_CAPTURE_CACHE_DIR, PDF_CAPTURE_ENGINE, PDF_CAPTURE_LOG_LEVEL, PDF_CAPTURE_MINERU_VENV, PDF_CAPTURE_OUTPUT_ROOT, PDF_CAPTURE_QDRANT_URL, PDF_CAPTURE_SEGMENT_TIMEOUT_S
Where it talks to
no vendor host named in the codeAlso aliyuncs.com, bigmodel.cn, minimaxi.com, moonshot.cn, deepseek.com, hf-mirror.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 aliyuncs.com, bigmodel.cn, minimaxi.com, moonshot.cn, deepseek.com, hf-mirror.com as well as its own vendor. The guard injects PDF_CAPTURE_EMBEDDING_API_KEY, PDF_CAPTURE_VLM_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx pdf-capture-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 81/100 (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
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsrc/pdf_capture_mcp/engines/mineru_engine.py:220 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/pdf_capture_mcp/engines/marker_engine.py:47 · Python subprocess execution detectedr = subprocess.run(["pkill", "-u", uid, "-f", pattern], capture_output=True, timeout=10)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Credential pass-through configurationsrc/pdf_capture_mcp/server.py:231 · Credential pass-through configuration — agent relays sensitive credentials" 2. Or pass api_key parameter directly (stored locally, never displayed)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Python subprocess execution detectedsrc/pdf_capture_mcp/engines/mineru_engine.py:48 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/pdf_capture_mcp/server.py:517 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandsrc/pdf_capture_mcp/llm_client.py:59 · File permission modification command — agent changes file ownership/permissionspass # Windows doesn't support chmodFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/test_scale_resilience.py:178 · Process kill command — agent can terminate processes# v0.9.5 blast-radius contract: every kill is scoped to the current userFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/pdf_capture_mcp/server.py:2094 · Process kill command — agent can terminate processes# breaker would kill every large scan (v0.10.0).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsrc/pdf_capture_mcp/server.py:1542 · Process kill command — agent can terminate processesexcept Exception as exc: # noqa: BLE001 — indexing must not kill conversionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/pdf_capture_mcp/engines/mineru_engine.py:60 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsrc/pdf_capture_mcp/server.py:1528 · Process kill command — agent can terminate processesexcept Exception as exc: # noqa: BLE001 — packaging must not kill conversionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈63 tok
1 file · 51 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 pdf-capture-mcp@0.12.0 as of 56 min ago. This is the package itself, not its dependencies.

pdf-capture-mcp@0.12.0 safety verdict: Verified (not started) — KillerSkills