Security

MCP Server for identity verification, enterprise check, vehicle query, OCR recognition and risk assessment in China.

The security layer for AI agents — platform-agnostic threat detection with 300+ rules, runtime blocking, and remediation guidance. Continuous protection.

Unified MCP server for Coherence Network — invite anyone or anything to ask what is alive, browse ideas and field stories, and contribute with attribution.

MCP server for safe shell, file, database, git, and HTTP access. Every operation validated against per-agent permission rules. Powered by AgentsID.

A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry.

iota embedded policy engine as a pi coding-agent extension: hash-pinned bless, agents.yaml enforcement for read/write/edit/bash, JSONL decision log

MCP Server scanner - eliminate black boxes by capturing JSON-RPC from connection to tools/list

MCP security trust-check for agents before installing MCPs, Skills or tools.

Model Context Protocol (MCP) server that enables your MCP client (e.g., Claude Desktop, Cline, Roo Code, Cursor, Windsurf, etc.) to interact with GitHub repositories using your GitHub personal access token.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

Dangerous config and secret scanner for AI coding agents, MCP, and local automation projects.

MCP security scanner. Scores any MCP server against the AgentsID trust framework and looks up pre-scanned results from the public registry.

Scan, score, and enforce security policies on MCP servers. Risk scoring (A-F), SARIF output, policy engine, drift detection, aguara integration, CI/CD gate.

jwt-lab – A fast, secure, beautiful JWT CLI tool and MCP server for developers & AI agents. Encode, decode, verify, inspect, audit, and generate keys for JSON Web Tokens.

URLCheck plugin for OpenClaw. Assess target URLs for potential threats and alignment with the user's browsing intent before agent navigation.

Wall data reader + self-hosted MCP server (single binary). Reads Wall export ZIPs and serves them locally for personal viewing, search, and LLM access.

The official command-line interface for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.

Ory plugin for Goose (Block's open-source agent CLI): scaffolding skills, a local Ory instance, and authentication, authorization, and audit for every tool call

Model Context Protocol (MCP) client support for Forgewisp agents — expose an MCP server's tools as agent FunctionDefinitions

Shared, consistent permission-prompt and policy layer for AI coding agent tools