Security

Model Context Protocol (MCP) plugin for Better Auth

Plug and play auth for Model Context Protocol (MCP) servers

Gmail MCP server with auto authentication support

Security auditor for AI agent configurations. Scans Claude Code setups for vulnerabilities, misconfigs, and injection risks.

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

Universal AI bridge for Obsidian vaults - connect any MCP-compatible assistant

Auth-aware Convex component that exposes selected Convex functions as MCP tools.

Static analysis scanner for MCP server code and multi-tenant SaaS applications. 57 deterministic rules covering tenant isolation, tool visibility, cache key scoping, RLS, IDOR, and credential vault isolation. MCP server for AI agent integration.

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

DeepSeek Harness MCP Connector and MCP Server marketplace with over one hundred MCP connectors, continuously updated. Discover, authorize, and manage connections in one place; supports OAuth 2.0 PKCE, API keys, stdio/HTTP, mcpServers JSON import, and tool

MCP interface for LUNO, the AI-era Backend Platform. Lets Claude Code, Cursor, and Codex build, operate, and govern production backends — schemas, content, forms, auth, storage, and publish. npx @luno-cms/mcp setup

The first open-source AI agent built for offensive security. Autonomous pentesting from your terminal.

WASM bindings for cedar-policy-mcp-schema-generator, exposing SchemaGenerator to JavaScript/TypeScript.

MCP server for automated web accessibility scanning with Playwright and Axe-core.

Reference implementation of the KYA-OS protocol for Model Context Protocol servers: identity, delegation, proofs, sessions, and verifiable audit trails

Permission hooks for AI coding agents: route tool approvals through Pushary push notifications

Trusty Squire signs up / in to websites for you so you don’t have to.

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.

Cross-agent permission policy specification for AI coding agents