ZBS Index What actually exists in applied AI, with the source next to it

mcp server

com.scopeblind/protect-mcp

Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.

Description as published by the maintainer. Source

  • version 0.10.0
  • active

active — Most recent push to the repository was 2026-07-09.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 9 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-07-09 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 4 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Package downloads 370 downloads Package downloads from the npm registry in this window. Includes continuous integration runs, mirrors and automated installs, so it overstates the number of human users. 2026-07-30 to 2026-08-05 npm
Latest published version 0.10.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-09 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License MIT Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-07-09 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub

Where to get it

Related, by what their authors tagged them

  • Aperion Shield — last commit 2026-08-04, shares policy-engine, zero-trust
    Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning
  • io.github.authzx/mcp-gateway — last commit 2026-07-13, shares access-control, policy-engine
    AuthzX MCP Gateway — policy-enforcing proxy between AI agents and MCP servers
  • io.github.dimitrilaouanis-tech/onyx-mcp — last commit 2026-07-31, shares signed-receipts
    Ed25519-signed ground-truth oracle — 63 paid x402 tools live on Base mainnet.
  • io.github.dns-aid/dns-aid — last commit 2026-08-06, shares ietf
    Discover and publish AI agents via DNS using SVCB records (RFC 9460)
  • Aegis — AI Agent Governance — last commit 2026-05-05, shares ai-security, audit-trail, policy-engine
    Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
  • io.github.cyanheads/cyanheads-mcp-server — last commit 2026-07-30, shares cloudflare-workers, gateway
    Fleet discovery for the cyanheads MCP ecosystem — semantic search + install snippets.
  • ToolTrust Scanner — last commit 2026-08-06, shares ai-security, gateway
    Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.
  • Gvnr — last commit 2026-06-11, shares rate-limiting
    Budget & cost control for AI agents — per-agent spend caps + rate limits before each call.
  • freellmpool — last commit 2026-07-29, shares rate-limiting
    Pool 18 LLM providers through MCP: ask, panel, tokenmax, route, models, quota, and stats.
  • io.github.berntpopp/genefoundry — last commit 2026-08-01, shares gateway
    MCP gateway federating 21 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.

These share tags the maintainers applied themselves, such as policy-engine, zero-trust, access-control, signed-receipts. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from scopeblind

How the author describes it

Topics the maintainer set on GitHub: access-control, ai-agent, ai-security, audit-trail, cedar, claude-desktop, cloudflare-workers, cursor, ed25519, gateway, ietf, mcp, mcp-server, policy-engine, rate-limiting, signed-receipts, zero, zero-trust.

Bring your own setup

We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.

Join ZBS AI Practice Lab

Sources

  1. scopeblind/scopeblind-gateway on GitHub — GitHub, observed , trust tier 3.
  2. protect-mcp download counts — npm, observed , trust tier 3.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.