Skills/PyPI/agenthive-mcp

agenthive-mcp@1.6.0

VERIFIED· not started

Publisher claims: "MCP server exposing AgentHive's shared team memory as native tools for Cursor and Claude Code" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher polarpoint-io · publishing for 64 daysInstalls 495Last detonated 2 h ago
$claude mcp add agenthive-mcp -- uvx agenthive-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
AGENTHIVE_TOKENConfiguration, not credentials: AGENTHIVE_HOOK_INCLUDE_TRANSCRIPT, AGENTHIVE_HOOK_STATE_DIR, AGENTHIVE_HOST, AGENTHIVE_MCP_SETUP_TOOLS, AGENTHIVE_TEAM_ID, AGENTHIVE_URL, HTTP_HOST, HTTP_PORT, TRANSPORT, XDG_STATE_HOME
Where it talks to
no vendor host named in the code
What we saw when it ran
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 AGENTHIVE_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 agenthive-mcp

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

What changed since 1.3.0

vet-skills diff agenthive-mcp 1.3.0 1.6.0

This version reaches for something 1.3.0 did not: 1 new credential variable (AGENTHIVE_TOKEN). Compared from the two recorded runs, not from source.

New credential variables
AGENTHIVE_TOKEN

1.3.0 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 2026-11-19 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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.3sprocessno install scripts to re-run

Static findings

LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_docimport.py:141 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filewrite(tmp_path, "AGENTS.md", "keep me")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_docimport.py:152 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filewrite(tmp_path, "AGENTS.md", "keep me")Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsrc/agenthive_mcp/hooklog.py:112 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agenthive_mcp/docimport.py:121 · Python subprocess execution detectedsubprocess.run(cmd, capture_output=True, text=True, timeout=300, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_docimport.py:172 · Python subprocess execution detectedsubprocess.run(["git", *args], cwd=repo, check=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_progressive_disclosure.py:274 · Python subprocess execution detectedreturn subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agenthive_mcp/codemap.py:63 · Python subprocess execution detectedout = 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_docimport.py:239 · Python subprocess execution detectedreturn subprocess.run(["git", "rev-parse", "HEAD"], cwd=repo,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agenthive_mcp/hooklog.py:252 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/agenthive_mcp/docimport.py:190 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_docimport.py:565 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filewrite(tmp_path, "AGENTS.md", "## Standards\n" + "real standard " * 5)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Instructs the agent to modify its persistent memory or instruction filestests/test_docimport.py:222 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction filewrite(tmp_path, "AGENTS.md", "## Standards\n" + "real content " * 5)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈60 tok
1 file · 30 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

Not checked against OSV yet; the weekly check has not reached this version.