Skills/PyPI/agent-comms-mcp

agent-comms-mcp@0.9.3

VERIFIED· not started

Publisher claims: "MCP service for permissioned, structured agent-to-agent communications" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher redesignhealth · publishing for 93 daysInstalls 1,757Last detonated 7d ago
$claude mcp add agent-comms-mcp -- uvx agent-comms-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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try agent-comms-mcp` runs it now and prints the full answer.

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 2026-11-07 and scored it 81/100 (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
0.1sprocessexec /usr/bin/date
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/agent-comms-mcp
0.1sclaimedno tools/list reply (exit 0)
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_local_proposal_flow.py:1106 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_db_models.py:972 · Python subprocess execution detectedres_down = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_local_proposal_flow.py:224 · Python subprocess execution detectedsubprocess.run(["docker", "rm", "-f", pg.container_id], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_local_proposal_flow.py:173 · Python subprocess execution detectedproc = subprocess.run(cmd, capture_output=True, text=True, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandproviders/comms.py:292 · Process kill command — agent can terminate processesmeant to be a real kill switch, but this function -- called on everyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_db_models.py:982 · Python subprocess execution detectedres_up1 = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_comms_tools.py:1145 · Process kill command — agent can terminate processes"""TECH-5736 suggestion: suspension is meant to be a real killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_local_proposal_flow.py:219 · Python subprocess execution detectedsubprocess.run(["docker", "rm", "-f", container_id], capture_output=True, check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_db_models.py:997 · Python subprocess execution detectedres_up2 = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_cross_brain_proposals.py:2 · Process kill command — agent can terminate processes``tests/test_proposal_service.py``. Covers the kill switch, targetFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsauth.py:102 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"See .env.example for the full list of required configuration."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_db_models.py:87 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandmain.py:84 · Process kill command — agent can terminate processes# Log configured proposal auto-approval kill switch and daily caps once at startup (TECH-8080 PR13).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_comms_tools.py:120 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_db_models.py:1007 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_local_proposal_flow.py:177 · Python subprocess execution detectedport_proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_comms_resources.py:109 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_proposal_endpoint.py:2592 · File type combined with upload action — agent may exfiltrate local data filesassert decide_resp.json()["sender_agent_id"] == str(agent.id)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Access to sensitive file pathstests/test_plugins.py:393 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesvar blank by accident (e.g. a blank line in a ``.env`` file)."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:681 · URL to a private-network address — a LAN or development targetrequest = client.build_request("GET", "https://10.0.0.1/actions/proposals/apply")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_proposal_tools.py:131 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_migration_accepted_types_optout.py:84 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_subscriptions.py:574 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:723 · URL to a private-network address — a LAN or development target"http://10.0.0.1:1055",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Access to sensitive file pathstests/test_plugins.py:338 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesa ``.env`` file)."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_migrations_offline.py:37 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:681 · URL to a private-network address — a LAN or development targetrequest = client.build_request("GET", "https://10.0.0.1/actions/proposals/apply")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_migrations_offline.py:641 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_schemas.py:832 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"file:///etc/passwd",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Authorization escalation languageREADME.md:81 · Authorization escalation language · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file| `comms_set_agent_shared` | `comms:write` (additionally requires `comms:admin` or an interactive/Okta caller) | Admin override of an existing agent's `is_shared` value, since `comms_register` freezesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:723 · URL to a private-network address — a LAN or development target"http://10.0.0.1:1055",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:724 · URL to a private-network address — a LAN or development target"http://192.168.1.1:1055",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL with embedded credentialstests/test_owner_reassignment_tool.py:350 · URL with embedded credentials — may be phishing or credential leaking"https://user:[email protected]", # userinfoFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
File type combined with upload actiontests/test_proposal_endpoint.py:2583 · File type combined with upload action — agent may exfiltrate local data filesassert get_resp.json()["sender_agent_id"] == str(agent.id)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandtests/test_proposal_service.py:2090 · Process kill command — agent can terminate processes# The kill switch guard sets decision_note on hold before committing under the row lock.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
URL to a private-network addresstests/test_proposal_apply_http_client.py:724 · URL to a private-network address — a LAN or development target"http://192.168.1.1:1055",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Process kill commandtests/test_proposal_service.py:1844 · Process kill command — agent can terminate processes# Returned proposal reflects human decision, NOT kill switch downgradeFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈55 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 agent-comms-mcp@0.9.3 as of 7 min ago. This is the package itself, not its dependencies.