Skills/PyPI/mcpaisuite-kernelmcp

mcpaisuite-kernelmcp@1.1.0

VERIFIED· not started

Publisher claims: "The sovereign orchestrator — connects all MCP AI suite libraries into an autonomous agent" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher gashel01 · publishing for 151 daysInstalls 25Last detonated 4d ago
$claude mcp add mcpaisuite-kernelmcp -- uvx mcpaisuite-kernelmcp
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
ANTHROPIC_API_KEYKERNELMCP_API_KEYSKERNELMCP_MAX_TOKENSOPENAI_API_KEYConfiguration, not credentials: KERNELMCP_API_HOST, KERNELMCP_API_PORT, KERNELMCP_CHECKPOINT_URL, KERNELMCP_CONTEXT_WINDOW, KERNELMCP_CORS_ORIGINS, KERNELMCP_DLP, KERNELMCP_DLP_ACTION, KERNELMCP_FAST_MODEL, KERNELMCP_JIT, KERNELMCP_LLM_PROVIDER, KERNELMCP_LOCAL_MODEL, KERNELMCP_MAX_COST, KERNELMCP_MAX_TURNS, KERNELMCP_MODEL, KERNELMCP_NAMESPACE, KERNELMCP_NANO, KERNELMCP_RBAC, KERNELMCP_ROUTING, MEMORYMCP_DECAY_MODE, MEMORYMCP_EPISODIC, MEMORYMCP_GRAPH, MEMORYMCP_SEMANTIC, MEMORYMCP_SQLITE_PATH, MEMORYMCP_WORKING, REDIS_URL, SANDBOXMCP_HOST_AUTO_APPROVE, WORKSPACEMCP_ROOT, WORKSPACEMCP_TENANT_ISOLATION
Where it talks to
no vendor host named in the code
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 ANTHROPIC_API_KEY, KERNELMCP_API_KEYS, KERNELMCP_MAX_TOKENS, OPENAI_API_KEY and talks to its vendor. 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 --net declared -- uvx mcpaisuite-kernelmcp

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 2026-11-10 and scored it 86/100 (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
Destructive command against a filesystem root or devicetests/unit/test_dry_run.py:83 · Destructive command against a filesystem root or deviceawait orch.execute_tool("exec_code", {"code": "rm -rf /"}, "ns")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandkernelmcp/core/nudges.py:28 · Process kill command — agent can terminate processescontent="BLOCKED. rm/sudo/kill forbidden via host_exec. To delete WORKSPACE files use delete_file tool instead."))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
AWS access key pattern detectedtests/unit/test_dlp.py:9 · AWS access key pattern detected — possible hardcoded or harvested keyAWS = "AKIA1234567890ABCDEF" # AKIA + 16 charsFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
File type combined with upload actionkernelmcp/cli.py:361 · File type combined with upload action — agent may exfiltrate local data files@click.option("--output", "-o", default="taskforce.json", help="Output file")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandkernelmcp/core/nudges.py:24 · Process kill command — agent can terminate processescontent="BLOCKED. rm/sudo/kill forbidden via host_exec. To delete WORKSPACE files use delete_file tool instead. To delete HOST files, tell the user to do it manually."))Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Destructive file system command detectedtests/unit/test_dry_run.py:83 · Destructive file system command detectedawait orch.execute_tool("exec_code", {"code": "rm -rf /"}, "ns")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈63 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 mcpaisuite-kernelmcp@1.1.0 as of 4d ago. This is the package itself, not its dependencies.