pdf-mcp@3.8.0
VERIFIED· not startedPublisher claims: "Agentic RAG over one PDF or a whole folder, with page-level evidence to check every answer: hybrid search, selective page reads, tables, OCR, charts, and CJK layouts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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_MCP_AUTH_TOKENConfiguration, not credentials: FPS, LOSSY, MAXCOLORS, OUT_GIF, PDF_MCP_ALLOW_ANY_PATH, PDF_MCP_BACKEND, PDF_MCP_BACKGROUND_EMBED, PDF_MCP_BACKGROUND_OCR, PDF_MCP_CACHE_DIR, PDF_MCP_CACHE_MAX_MB, PDF_MCP_CACHE_TTL, PDF_MCP_CUDA, PDF_MCP_HTTP_HOST, PDF_MCP_HTTP_PATH, PDF_MCP_HTTP_PORT, PDF_MCP_MAX_WORKERS, PDF_MCP_OCR, PDF_MCP_VECTOR_CACHE_MB, SCENE_H, SCENE_W, TESSDATA_PREFIX- Where it talks to
- no vendor host named in the codeAlso sourceforge.net, arxiv.org — 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 sourceforge.net, arxiv.org as well as its own vendor. The guard injects PDF_MCP_AUTH_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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 89/100 (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 deviationsStatic findings
result = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.// npx playwright install chromiumFix: Pin versions and sources; vendor anything fetched at install time.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(cmd, cwd=INFRA_DIR, env=_cdk_env(), check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(cmd, capture_output=capture_output, text=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([*shlex.split(editor), str(path)], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([exe, "--version"], capture_output=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.login_result = subprocess.run(["gh", "auth", "login"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# different user, where chmod raises PermissionError. A best-effortFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.Cost to the agent
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-mcp@3.8.0 as of 50 min ago. This is the package itself, not its dependencies.