Search

An MCP server for analyzing PCAP files.

A Model Context Protocol server for .NET assembly reverse engineering (ILSpy/ICSharpCode.Decompiler)

Open source hooks library for AI coding agents - Install safety, quality, and automation hooks with a single command

Local-First Zero-Trust MCP Privacy Firewall & Context-Diet Gateway

Reads .mcp.json / .vscode/mcp.json / claude_desktop_config.json while you edit it and marks the lines that hand an AI agent more than you meant - unpinned servers, literal credentials, plaintext trans

Open-source reference implementation of the IETF agent-identity stack — OAuth 2.1 + identity-chaining + transaction-tokens + DPoP + MCP

Astro integration that exposes your site content via WebMCP for AI agents

Confirm-before-act for MCP: write tools become pending actions that only the user's own voice or tap can release.

OpenMetadata context provider for akko-mcp-trino: descriptions, owners, tiers, PII classifications and keys, handed to the agent alongside the columns.

Dynamic red-team harness for MCP agents: a transparent proxy that injects attacks, measures attack success rate, and ships an information-flow mitigation layer.

PromptGuard MCP server — scan prompts, redact PII, and audit LLM SDK usage from any MCP client

OPNsense firewall operations via API & mcp. Query ARP, DHCP, firewall rules, logs, interfaces, system status, and packet capture via STDIO or SSE.

Find every AI agent skill in your repos, spot the duplicates teams keep rebuilding, and catch the risky ones. Claude Code, Codex, Cursor, Copilot, Gemini, Windsurf and MCP.

Trust scanning for MCP servers: static heuristics plus behavioral evals, with signed version-pinned trust badges. The place you check before you install an MCP server.

Stdio MCP server exposing Blekline governance tools for all [verified client surfaces](https://github.com/Blekline/blekline-oss/tree/main/integrations).

https://github.com/thyn-ai/algenta-sdk/tree/main/packages/mcp

[](https://glama.ai/mcp/servers/vaulted-fyi/vaulted-mcp-server) 📇 🏠 🍎 🪟 🐧 - Share encrypted, self-destructing secrets from your AI agent. Zero-knowledge E2E encryption. Agent-blind input sources (env:, file:, dotenv:) keep secrets out of LLM context.

A permission layer for AI agent tool calls — wrap any MCP server and enforce allow/deny/ask policy with full audit.

Auto-fitted pivot tables that toggle to histograms and back, with slicing, clustering, Markov chains, paging for big data, an MCP server for LLM agents and Jupyter menus. For cyber logs or any tabular data.

DevOps autopilot for Claude Code -- scan vulns, fix deps, review PRs, gen tests, track DORA metrics, multi-perspective project reviews. 21 commands, zero config.