Skills/PyPI/3tears-mcp

3tears-mcp@0.94.0

VERIFIED· install only

Publisher claims: "Shared MCP framework: McpServer + McpTool + PlatformHttpClient + per-tool RBAC backed by mcp_tool_grants and the task-02 epoch broadcast" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pacepace · publishing for 137 daysInstalls 6,737Last detonated 30 min ago
$claude mcp add 3tears-mcp -- uvx 3tears-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
no credential variables read in the code
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
use of the skill by an agent

Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx 3tears-mcp

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

What changed since 0.77.0

vet-skills diff 3tears-mcp 0.77.0 0.94.0

In the sandbox, this version reached for nothing 0.77.0 did not. Compared from the two recorded runs, not from source.

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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 87/100 (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
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'threetears'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'httpx'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'uvicorn'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'uuid_utils'
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexited 1: ModuleNotFoundError: No module named 'jsonschema'
0.5sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: ModuleNotFoundError: No module named 'jsonschema'
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocessexited 1: ModuleNotFoundError: No module named 'threetears'
0.6sprocess7 of 7 bundled scripts run with no arguments
0.6sprocessscript backend runs setup only
0.6sprocessscript backend runs setup only
0.6sprocessno install scripts to re-run

Static findings

MEDIUM
MCP server using network transport (SSE/HTTP)src/threetears/mcp/server.py:657 · MCP server using network transport (SSE/HTTP) — data sent over networkblock, the same two faces a successful structured result has. :class:`McpServer` passes itFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill commandtests/unit/test_auth.py:558 · Process kill command — agent can terminate processes"""a tick that raises does not kill the loop; subsequent ticks fire.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/unit/test_imports_without_grants.py:113 · Python subprocess execution detectedreturn subprocess.run([sys.executable, "-c", code], capture_output=True, text=True, check=False, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)pyproject.toml:8 · MCP server using network transport (SSE/HTTP) — data sent over networkdescription = "Shared MCP framework: McpServer + McpTool + PlatformHttpClient + per-tool RBAC backed by mcp_tool_grants and the task-02 epoch broadcast"Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)src/threetears/mcp/server.py:563 · MCP server using network transport (SSE/HTTP) — data sent over network"McpServer.build_http_transport called before start; the authorizer "Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)src/threetears/mcp/server.py:523 · MCP server using network transport (SSE/HTTP) — data sent over network"McpServer.build_http_app called before start; the authorizer "Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:6 · MCP server using network transport (SSE/HTTP) — data sent over networkShared MCP framework: McpServer + McpTool + PlatformHttpClient + per-tool RBAC backed by mcp_tool_grants and the task-02 epoch broadcastFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈70 tok
1 file · 31 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

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