Search

MCP server for Verdix: check an EVM address on Base before sending it funds (safe/caution/danger). Pays per call via x402 from your own wallet, with a max-price cap.

Presentation layer — MCP server with stdio and HTTP transports.

SAPL Policy Enforcement Point (PEP) integration for FastMCP

Mantivor — runtime monitoring collector for MCP servers

Optimus Labs MCP server — read-only access to your org's agent inventory, findings, and shadow-AI discovery signals

The mcp-warden binary for win32-x64. Installed by @mcp-warden/cli; not meant to be used on its own.

Temporary package placeholder for staged publishing

Runs Iris, the MCP server that scores every agent output for quality, safety and cost. The server is @iris-eval/mcp-server; this package makes `npx iris-eval` start it, at the server's latest release.

The hardening & conformance standard for MCP servers. (Name reserved — first release coming soon.)

Reusable Rust building blocks for Model Context Protocol servers and clients

Shared configuration, workflows, and architectural patterns for the Forgespace ecosystem

🐍 Amorce Python SDK - Ed25519 signatures for AI agents

[Unofficial/Community] MCP server for Wireshark/tshark integration with AI tools

MCP server for analyzing PE, ELF, and Mach-O binaries using LIEF

EU-hosted website monitoring + 17-framework compliance MCP. One anonymous tool, four authenticated.

Hash-chained HMAC-signed audit log MCP for A2A (agent-to-agent) calls. Every tool-call, agent-handoff, decision gets a tamper-evident signed record. EU AI Act Art 12 automatic logs, DORA Art 17 ICT incident logs, ISO 42001 clause 9 monitoring — auditor-ready end-of-day attestations. By MEOK AI Labs.

AI-powered GitHub issue triage, PR review, and sprint planning - Vercel AI SDK primitives

Local MCP configuration risk scanner for Claude, Cursor, Windsurf, and agent tools.

A reversibility layer for agentic tool use — a transparent MCP proxy that classifies which tool calls can be taken back, synthesises inverse operations, keeps a durable cross-server undo log, and interrupts you only for genuinely irreversible actions.

Vulnerability and exploit intelligence for AI assistants (370K+ CVEs, 105K+ exploits)