Skills/PyPI/singularis-mcp

singularis-mcp@0.1.12

VERIFIED· not started

Publisher claims: "Bring us your hardest problems. Free tryout, credits up front; sharing results is requested, not required. Free keys run hosted (nothing to install). Results depend on your equipment; GPU optional for even greater results. MCP server for AI agents; client shell only, no engine code." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server) · listed in the official MCP RegistryPublisher oov1317 · publishing for 34 daysInstalls 532Last detonated 1 h ago
$claude mcp add singularis-mcp -- uvx singularis-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
SINGULARIS_API_KEYSINGULARIS_SHELL_SECRETConfiguration, not credentials: SINGULARIS_ENGINE_CMD, SINGULARIS_ENGINE_METERED, SINGULARIS_ENGINE_URL, SINGULARIS_GATEWAY, SINGULARIS_HOME, SINGULARIS_INLINE_MAX, SINGULARIS_RESULT_DIR
Where it talks to
getsingularis.com (its own)
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. It asks for SINGULARIS_API_KEY, SINGULARIS_SHELL_SECRET and talks to getsingularis.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets SINGULARIS_API_KEY=getsingularis.com,SINGULARIS_SHELL_SECRET=getsingularis.com -- uvx singularis-mcp

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

What changed since 0.1.11

vet-skills diff singularis-mcp 0.1.11 0.1.12

In the sandbox, this version reached for nothing 0.1.11 did not. Compared from the two recorded runs, not from source.

0.1.11 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 2026-11-18 and scored it 90/100 (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 detectedsingularis_mcp/client.py:399 · Python subprocess execution detectedproc = subprocess.run(cmd, shell=True, input=json.dumps(job).encode(), capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandsingularis_mcp/client.py:401 · Process kill command — agent can terminate processes# grokfix F8 (customer test): exit 124 is a timeout killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈109 tok
1 file · 18 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 singularis-mcp@0.1.12 as of 30 min ago. This is the package itself, not its dependencies.