Skills/PyPI/spark-mcp

spark-mcp@0.5.0

VERIFIED· not started

Publisher claims: "Spark Connect (gRPC) API + MCP Server for Agentic AI!" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher repository-maintainers-maintainers · publishing for 441 daysInstalls 1,284Last detonated 1 h ago
$claude mcp add spark-mcp -- uvx spark-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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso apps.svc — 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx spark-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 87/100 (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

LOW
Dynamic module loadingtests/test_scion_sdk_0_10_imports.py:37 · Dynamic module loadingand importlib.util.find_spec(alias.name) is NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_scion_sdk_0_10_imports.py:45 · Dynamic module loadingif importlib.util.find_spec(node.module) is None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandspark_mcp/skills/spark-job-control/SKILL.md:29 · Process kill command — agent can terminate processes3. Call the kill tool with `confirm` set, then read the status again.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandspark_mcp/skills/spark-job-control/SKILL.md:28 · Process kill command — agent can terminate processes2. Prefer `spark_cancel` by tag over a kill when the work was tagged.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_scion_sdk_0_10_imports.py:52 · Dynamic module loadingif importlib.util.find_spec(f"{node.module}.{alias.name}") is None:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionspark_mcp/api/api_client_spark.py:483 · File type combined with upload action — agent may exfiltrate local data filesSQL transforms run via ``spark.sql(body)`` with every declared input rewrittenFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandspark_mcp/api/api_client_rest.py:367 · Process kill command — agent can terminate processes"""Kill one running stage on the live driver (Spark UI kill endpoint)."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontests/test_rest_operations.py:96 · File type combined with upload action — agent may exfiltrate local data filesassert Api.sql.__http_method__ == "POST"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandspark_mcp/skills/spark-job-control/SKILL.md:6 · Process kill command — agent can terminate processesoperations by tag, kill a job or a stage, and check the application status. UseFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python exec or eval of computed codespark_mcp/api/api_client_spark.py:529 · Python exec or eval of computed codedf = eval( # nosec B307 - constrained namespace, write- and approval-gatedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandspark_mcp/connector_contracts.py:528 · Process kill command — agent can terminate processesdescription="Cancel by tag or kill a job or stage after reading it.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandspark_mcp/skills/spark-history-monitoring/SKILL.md:9 · Process kill command — agent can terminate processesto cancel or kill running work (use spark-job-control) or to run SQL (useFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandspark_mcp/api/api_client_rest.py:359 · Process kill command — agent can terminate processes"""Kill one running job on the live driver (Spark UI kill endpoint)."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandspark_mcp/skills/spark-job-control/SKILL.md:5 · Process kill command — agent can terminate processesCancel or kill running Spark work through the spark-mcp MCP server — cancelFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈3,682 tok
6 files · 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 spark-mcp@0.5.0 as of 48 min ago. This is the package itself, not its dependencies.