Skills/PyPI/saferagenticai-mcp

saferagenticai-mcp@0.4.2

VERIFIED· not started

Publisher claims: "MCP server exposing the SaferAgenticAI safety framework (canonical criteria + Implementation Patterns layer) to coding assistants." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher nellinc · publishing for 213 daysInstalls 474Last detonated 1 h ago
$claude mcp add saferagenticai-mcp -- uvx saferagenticai-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
MCP_DOMAIN_VERIFICATION_TOKENConfiguration, not credentials: MCP_HTTP_HOST, MCP_HTTP_PORT, MCP_TRANSPORT
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 MCP_DOMAIN_VERIFICATION_TOKEN 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 saferagenticai-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 2026-11-16 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
Process kill commandsaferagenticai_mcp/_data/suites/D3/D3--idx6--overseeing-monitoring-agents.yaml:119 · Process kill command — agent can terminate processes- name: Watchdog can kill but humans cannot restoreFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsaferagenticai_mcp/_data/suites/D3/D3--idx0--security.yaml:258 · Process kill command — agent can terminate processes- D4 for human override / shutdown authority (see also D3.5 kill switch)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssaferagenticai_mcp/_data/operational_heuristics.yaml:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdescription: "Declarative deny list for .env, credentials, secrets, .pem, .key files"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssaferagenticai_mcp/_data/operational_heuristics.yaml:313 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdescription: "Blocks writes to .env files (credential exposure prevention)"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssaferagenticai_mcp/_data/operational_heuristics.yaml:259 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesshell commands) and env-protection.cjs (blocks .env file writes).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandsaferagenticai_mcp/_data/suites/D5/D5--idx1--logging-of-internal-goals.yaml:86 · Process kill command — agent can terminate processessketch: 'Do not inline full reasoning traces into every goal event — size will kill the log. Store tracesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandsaferagenticai_mcp/server.py:632 · Process kill command — agent can terminate processes# Synonym phrases ("kill switch", "near miss") are matched on the rawFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
False authorization claimsaferagenticai_mcp/_data/suites/D3/D3--idx1--authorization.yaml:99 · False authorization claim — impersonating privileged role · informational: not an instruction filewhy_wrong: '"I am the admin" in a prompt is not authorization. The cryptographic identity of the callingFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionsaferagenticai_mcp/_data/suites/D3/D3--idx6--overseeing-monitoring-agents.yaml:116 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileA jailbreak that defeats the monitored model defeats its twin.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandsaferagenticai_mcp/_data/suites/I5/I5--idx2--self-improving-architectures.yaml:82 · Process kill command — agent can terminate processes- name: Weight-modification kill switchFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Prompt injection attemptsaferagenticai_mcp/_data/suites/D3/D3--idx11--model-poisoning.yaml:116 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileA retrieved document containing "ignore previous instructions andFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Process kill commandsaferagenticai_mcp/query_vocabulary.py:32 · Process kill command — agent can terminate processes(("kill switch", "killswitch", "emergency stop", "e-stop", "stop button"),Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈72 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 saferagenticai-mcp@0.4.2 as of 40 min ago. This is the package itself, not its dependencies.