Agent Skills Index

Directory / Claude community plugins (Anthropic) / protect-mcp

protect-mcp

plugin Security

MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call without blocking. Enforce mode applies per-tool allow/deny/rate-limit/approval policies. Every decision is cryptographically signed and independently verifiable offline. MIT licensed. IETF Internet-Draft published for the receipts protocol.
Description from the marketplace entry / plugin manifest.

Information source

Copied from the Claude community plugins (Anthropic) catalog (anthropics/claude-plugins-community), maintained by Anthropic (community submissions).

Links are pinned to commit 06ec7b6 (2026-10-13), the version we synced. Not reviewed by us.

Install

Add the marketplace (once, in Claude Code)
/plugin marketplace add anthropics/claude-plugins-community
In a Claude Code session
/plugin install protect-mcp@claude-community
From your shell
claude plugin install protect-mcp@claude-community

Commands follow each host's documentation (Claude Code, Claude Cowork docs). gh skill needs GitHub CLI 2.90 or later and is in public preview.

Listed from Anthropic (community submissions)'s catalog, not reviewed by us. Read the source before installing.

Catalog
Claude community plugins (Anthropic) (claude-community)
Information source
marketplace.json in anthropics/claude-plugins-community
Author
Not stated in the source
Source code
tomjwxf/protect-mcp-plugin
Homepage
scopeblind.com/docs/protect-mcp
License
MIT (repository license)
Repository stars
0 for tomjwxf/protect-mcp-plugin
Added to catalog
2026-03-31
Last change
2026-10-26 (last push to the repo)

What it contains

Hosted in an external repository, so contents are not counted here. See the source link.

Similar in Security