Huddle (kolotovalexander) MCP Server
mcp-huddle
PyPI
v0.5.0
Published by kolotovalexander — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Persistent multi-agent chat MCP server with web dashboard. Rooms where AI agents huddle to discuss, critique, and decide.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 4
high Shell/command execution in server code (src/mcp_huddle/mimo_runner.py)MTC-SRC-002
In the server's implementation (`src/mcp_huddle/mimo_runner.py:94`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: time.time() proc = subprocess.run( argv, capture_output=True, text=True, timeout=ti
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/mcp_huddle/mimo_runner.py
high Shell/command execution in server code (src/mcp_huddle/spawn.py)MTC-SRC-002
In the server's implementation (`src/mcp_huddle/spawn.py:680`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: proc = subprocess.Popen( argv, cwd=cwd or None, stdin=subprocess.DE
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/mcp_huddle/spawn.py
high Shell/command execution in server code (src/mcp_huddle/static/dashboard.js)MTC-SRC-002
In the server's implementation (`src/mcp_huddle/static/dashboard.js:73`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: 'set.spawn': 'Agents & spawn (env)', 'set.agentPrompt': 'Agent setup prompt', 'tip.spawn': 'Environment variables t
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/mcp_huddle/static/dashboard.js
low Shell/command execution in packaging/dev tooling (tests/test_phase1_2.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_phase1_2.py:1214`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: estores the full-access spawn (worker mode).""" monkeypatch.setenv("MCP_HUDDLE_READONLY", "0") monkeypatch.delen
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_phase1_2.py
Tools 12
Each tool and what it can reach — statically extracted from the published source.
message_postno sensitive capabilitymessages_readno sensitive capabilitynotify_registerno sensitive capabilitypropose_resolutionno sensitive capabilityresolution_voteno sensitive capabilityroom_createno sensitive capabilityroom_infono sensitive capabilityroom_inviteno sensitive capabilityroom_listno sensitive capabilityroom_reclaimno sensitive capability
Show 2 more tools ↓
room_round_advanceno sensitive capabilityroom_summarizeno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.5.0 latest |
A 93/100 | 4 | 1.12.1 | 2026-07-27 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcp-huddle --online --registry pypiOther implementations of Huddle 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Marketing & Social
Official Abyssfall game info, newsletter double opt-in, and merch reservation tools.
AdCritter ads platform: docs, API reference, app scaffolding, and white-label integration.
Google AdSense MCP Server - Monitor earnings, reports, and account health via Claude/AI
Operational empathy for technical founders + PE/VC operators navigating high-stakes B2B interactions. 28 MCP tools + CLI: ICP scoring, persona simulation, battlecards, deal classification, prospect discovery, investor matching, founder wellness, plus mark
MCP server for Bing Webmaster Tools — SEO site management, URL submission, sitemaps, stats, keywords
MCP (Model Context Protocol) server that helps AI agents use Primer Brand (@primer/react-brand) correctly when building GitHub marketing and landing pages.