Skills/PyPI/sie-mcp

sie-mcp@0.11.1

CAUTION· not started

Publisher claims: "SIE MCP edge - hosted MCP server exposing SIE document jobs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 727 daysInstalls 406Last detonated 1 h ago

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: Caution 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
SIE_API_KEYSIE_MCP_CONNECTOR_SECRETSIE_MCP_CONNECTOR_SECRETSSIE_MCP_OAUTH_REDIRECT_URIS or --connector-secretConfiguration, not credentials: SIE_BASE_URL, SIE_MCP_ALLOWED_HOSTS, SIE_MCP_CAPTION_MODEL, SIE_MCP_DOCLING_MODEL, SIE_MCP_DOCS_GPU, SIE_MCP_EMBED_MODEL, SIE_MCP_ENCODE_MODEL, SIE_MCP_EXTRACT_GPU, SIE_MCP_EXTRACT_MODEL, SIE_MCP_GENERATE_GPU, SIE_MCP_GENERATE_MODEL, SIE_MCP_GPU, SIE_MCP_IMAGE_GPU, SIE_MCP_IMAGE_LABELS, SIE_MCP_PII_MODEL, SIE_MCP_PUBLIC_URL, SIE_MCP_QA_GPU, SIE_MCP_RERANK_MODEL, SIE_MCP_VLOCR_MODEL
Where it talks to
no vendor host named in the codeAlso claude.ai — 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 claude.ai as well as its own vendor. The guard injects SIE_API_KEY, SIE_MCP_CONNECTOR_SECRET, SIE_MCP_CONNECTOR_SECRETS, SIE_MCP_OAUTH_REDIRECT_URIS only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sie-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 2026-11-18 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Image alt text carrying instructions. 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

CRITICAL
Prompting user to enter sensitive credentialssrc/sie_mcp/cli.py:96 · Prompting user to enter sensitive credentials — social engineering"Provide the secret during connector installation."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedtests/test_plugin_pack.py:261 · Python subprocess execution detectedresult = subprocess.run( # noqa: S603 - executes the generated command in an isolated shell fixture.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Image alt text carrying instructionsREADME.md:22 · Image alt text carrying instructionsSIE MCP edge architecture: Claude connects over MCP to the sie-mcp edge in your VPC, which holds the cluster credential and calls the SIE gateway and GPU workerFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈4,072 tok
5 files · 80 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 sie-mcp@0.11.1 as of 52 min ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypiPropose a patch to the maintainer