Intake notes: vetting this one costs metered API spend, so it’s deferred by the house rule until Gatehouse earns revenue. It routes to third-party models (Gemini, GPT) and needs paid keys to exercise, and the no-metered-spend rule forbids that pre-revenue. When it’s vetted: measure the injected tool-schema overhead and flag the metered-spend implication prominently, since running it bills whoever holds the key.
zen-mcp-server
• Not yet vettedRoutes work to other models (Gemini, GPT, local) as second opinions inside one session: extended reasoning, review, and consensus workflows.
In the intake queue. Listed with facts only; no verdict until a human runs it.
by Beehive Innovations MCP server Orchestration
Quiet for 10 months passing liveness · checked Oct 19, 2026
Commit activity · last 52 weeks
Stars12k
LanguagePython
Open issues150
Pricingfree
ListedJul 11, 2026
Facts pulled from the source repo and refreshed nightly. Stars are a data point, not our ranking. We don't order by popularity.
Runs in
| Harness | Support | Notes |
|---|---|---|
| Claude Code | untested | — |
| Any MCP client | untested | — |
Support levels reflect what we actually ran, not what the README claims. untested means exactly that.
What a vet will check
- Whether it can act or write when told not to (read-only and scope enforcement)
- What it injects per session: token cost and the size of the tool surface
- Where your data goes: any call that leaves your machine, disclosed or not
No verdict is published until a human installs it, runs it, and audits what it injects. How vetting works →
