Covenant Guard
org.opencovenant/guard
Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.
Description as published in the official MCP registry.
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 8 | github.com/open-covenant/covenant |
| Last push | 2026-10-04 | GitHub API |
| Licence | Apache-2.0 | GitHub API |
| Registry version | 0.1.1 · active · updated 2026-07-13 | registry |
| Package | mcpb: https://github.com/open-covenant/covenant/releases/download/covguard-v0.1.1/covenant-guard.mcpb | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Related servers
- Mizuki Fixed-price maintenance for public GitHub issues, paid in USDC on Solana.
- healthclaw-guardrails Guardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant…
- HOL Guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio…
- Limitguard Trust Intelligence Entity verification, sanctions screening, and trust scoring for AI agents via x402…
- tokenguard-mcp Real-world data for agents: air quality, geocoding, quakes, holidays, web search
- presign-guard Pre-sign, token and approval checks for agents: green/orange/red for signatures, tokens…
Badge for your README
Shows the result of our latest check and links back to this page.
[](https://openforallofus.com/tools/org.opencovenant/guard)Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name org.opencovenant/guard.