Skills/PyPI/streamlit-mcp

streamlit-mcp@0.14.4

CAUTION· not started

Publisher claims: "Serve an existing Streamlit app as an MCP server — agents drive it natively, no browser." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher dkedar7 · publishing for 151 daysInstalls 5,562Last detonated 3 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
OPENROUTER_API_KEY or --bearer-token
Where it talks to
no vendor host named in the codeAlso openrouter.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 openrouter.ai as well as its own vendor. The guard injects OPENROUTER_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

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

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

What changed since 0.8.0

vet-skills diff streamlit-mcp 0.8.0 0.14.4

This version reaches for something 0.8.0 did not: 1 new host (openrouter.ai) · 1 new credential variable (OPENROUTER_API_KEY). Compared from the two recorded runs, not from source.

New hosts
openrouter.ai
New credential variables
OPENROUTER_API_KEY

0.8.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-19 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. 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

HIGH
Access to sensitive file pathsarena/__init__.py:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import ArenaEnvFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsarena/agents.py:17 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import ArenaEnv, StepBudgetExceededFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsarena/mcp_env.py:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import Step, StepBudgetExceededFix: 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 actiontests/test_runtime.py:300 · File type combined with upload action — agent may exfiltrate local data files"""st.json serializes a whole structure, so one output could otherwise crowd out the rest ofFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
HTML comment carrying imperative instructions to the agentdocs/changelog.md:1 · HTML comment carrying imperative instructions to the agentIncluded verbatim from the repo root so the docs never drift from the canonical changelog.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_v0100_features.py:247 · MCP server using network transport (SSE/HTTP) — data sent over networkassert json.loads(out)["mcpServers"]["streamlit-mcp"]["url"] == "http://127.0.0.1:8000/mcp"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
HIGH
Access to sensitive file pathsarena/llm.py:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import ArenaEnv, StepBudgetExceededFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsarena/runner.py:9 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesfrom .env import ArenaEnv, StepBudgetExceededFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Dynamic module loadingarena/registry.py:21 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module) # type: ignore[union-attr]Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingarena/registry.py:20 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)tests/test_v0100_features.py:255 · MCP server using network transport (SSE/HTTP) — data sent over networkassert json.loads(out)["mcpServers"]["streamlit-mcp"]["url"] == "http://[::1]:8000/sse"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈59 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 streamlit-mcp@0.14.4 as of 2 h ago. This is the package itself, not its dependencies.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim dkedar7: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  6. Dynamic module loading≈ +1 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim dkedar7Propose a patch to the maintainer