A security add-on that applies Cedar rules, a policy language for deciding what actions are allowed, and creates Ed25519-signed records for Claude Code tool calls.

It is for controlling Claude Code tool calls with policies and recording them with cryptographic signatures.

It helps enforce rules around tool use and provides signed records that can show what calls were made.

protect-mcp — Plugin by VeritasActa

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add VeritasActa/verify

agentmods

npx agentmods add plugins/veritasacta/verify/protect-mcp

Clone the repo

git clone --depth 1 https://github.com/VeritasActa/verify

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

protect-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ecosystem/wshobson-plugin/protect-mcp/.claude-plugin/plugin.json · 24 lines

The source is not reproduced here

No licence file

Read it on GitHub

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 24 lines scan A 4a8a4da8e15f

Subscribe to this mod's changes

protect-mcp is a plugin published in the GitHub repository VeritasActa/verify (5 stars, last pushed 3mo ago), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Security anonymous-credentials cryptography privacy rate-limiting rfc9497 voprf

toolkit-mcp-server

Fast developer utilities — random ID generation, QR codes, IP geolocation, hashing, and encoding — plus gated, fail-closed network and system diagnostics.

cyanheads/toolkit-mcp-server · not measured

ai-watermark-remover marketplace

Anti-detection hygiene skills: invisible Unicode, statistical text watermarks, and C2PA/EXIF/XMP provenance metadata.

mohityadav8/ai-watermark-remover · not measured

ai-watermark-remover

Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B), and C2PA/EXIF/XMP/container metadata on images, documents, and media. Ships the remove-ai-marks skill (thin client over the repo's HTTP service) and the self-contained clean-user-facing-text skill.

mohityadav8/ai-watermark-remover · not measured

searxng marketplace

Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional ren.

88plug/searxng-mcp · not measured

searxng

Fast, token-efficient MCP for SearXNG metasearch. Privacy-respecting search across 70+ engines with stdio + streamable-http transports, Docker, and optional rendered (Playwright) fetch for JS-heavy pages. Self-hostable. The underlying server is also usable independently of Claude Code via uvx --from git+https://github.