MCP server Claude CodeCodexCursor +2
Local-first privacy MCP server for sensitive AI workflows. Runs locally from the securedact-mcp Python package.
not rated 2
+1 yesterday A
tokens not measured
original Apache-2.0
mcpkernel
50MCP server Claude CodeCodexCursor +2
MCP server "mcpkernel" as configured in piyushptiwari1/mcpkernel. Launched with mcpkernel serve --host 127.0.0.1 --port 8000. Needs 1 environment variable to run.
not rated 2
+1 2mo ago A
tokens not measured
original Apache-2.0
skilltotal
51MCP server Claude CodeCodexCursor +2
AI Component Security Platform — static security analysis for AI components (CLI engine). Runs locally from the skilltotal Python package.
not rated 1 5d ago A
tokens not measured
original Apache-2.0
agent-sec
52MCP server Claude CodeCodexCursor +2
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP. Remote server at agentsec.kernora.ai.
not rated 1 1mo ago A
tokens not measured
original Apache-2.0
mcp
53MCP server Claude CodeCodexCursor +2
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM. Runs locally from the @safeprompt.dev/mcp npm package. Needs 3 environment variables to run.
not rated 1 19d ago A
tokens not measured
original MIT
aisentinel
54MCP server Claude CodeCodexCursor +2
MCP server "aisentinel" as configured in Kabzhanov/AISentinel. Launched with https://github.com/Kabzhanov/AISentinel/releases/download/v1.0.6/aisentinel-v1.0.
not rated 1 1mo ago A
tokens not measured
yagami
55MCP server Claude CodeCodexCursor +2
Open-source AI context firewall for governed model, retrieval, memory, and tool access. Runs locally from the yagami Python package. Needs 3 environment variables to run.
not rated 1 4d ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics. Runs locally from the sentinel-scan-cli npm package.
not rated 1 11d ago A
tokens not measured
original MIT
aileron
57MCP server Claude CodeCodexCursor +2
Flight recorder for AI agents: tamper-evident audit logging, policy enforcement, and incident reports. Runs locally from the aileron Python package.
not rated 1 yesterday A
tokens not measured
original Apache-2.0
mcp-server
58MCP server Claude CodeCodexCursor +2
Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails. Runs locally from the @declaw/mcp-server npm package. Needs 2 environment variables to run.
not rated 1 23d ago A
tokens not measured
original Apache-2.0
codesafer
59MCP server Claude CodeCodexCursor +2
Scans AI-generated code for invisible Unicode, Trojan Source, and supply-chain threats. Runs locally from the cleaner-code npm package.
not rated 1 4mo ago A
tokens not measured
original MIT
mcp-rampart
60MCP server Claude CodeCodexCursor +2
Security toolkit for FastAPI-based MCP servers — pre-flight audit + runtime prompt-injection guardrail. Runs locally from the mcp-rampart Python package.
not rated 1 3mo ago A
tokens not measured
original MIT
oathe-mcp
61MCP server Claude CodeCodexCursor +2
MCP server for Oathe AI security audits — check trust scores before installing MCP servers, plugins, or AI agent skills. Runs locally from the oathe-mcp npm package.
not rated 1 6mo ago A
tokens not measured
original MIT
zugashield
62MCP server Claude CodeCodexCursor +2
AI Agent Security System - 7-layer defense against prompt injection, data exfiltration, and AI-specific attacks. Runs locally from the zugashield Python package.
not rated 1 5d ago A
tokens not measured
original MIT
secretproxy
63MCP server Claude CodeCodexCursor +2
MCP server "secretproxy" as configured in AliProgrammin/agentic-vault. Runs locally from the secretproxy npm package.
not rated 1 4mo ago A
tokens not measured
AGPL-3.0
github
64MCP server Claude CodeCodexCursor +2
One of 5 in claude_desktop_config.json
MCP server "github" as configured in cognis-digital/mcpharden. Runs in Docker (ghcr.io/example/github-mcp:1.4.2). Needs 1 environment variable to run.
not rated 1 2mo ago A
tokens not measured
archived
MCP server Claude CodeCodexCursor +2
MCP server "cognis-ragshield" as configured in cognis-digital/ragshield. Runs locally from the cognis-ragshield Python package.
not rated 1 2mo ago A
tokens not measured
MCP server Claude CodeCodexCursor +2
Autonomous security scanner for AI agents. Detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities. Runs locally from the dfx-agentguard Python package.
not rated 1 1mo ago A
tokens not measured
LGPL-3.0
promptwall
67MCP server Claude CodeCodexCursor +2
LLM prompt injection firewall with session tracking, explainability and multilingual detection. Runs locally from the promptwall Python package.
not rated 1
+1 20d ago A
tokens not measured
original MIT
MCP server Claude CodeCodexCursor +2
MCP server "nullsec-redteam-ai" as configured in Panda1847/NullSec-RedTeam-AI. Runs locally from the nullsec-redteam-ai Python package.
not rated 1 18d ago A
tokens not measured
original MIT
brian-mitchell-sec/workspace-tools-mcp
MCP server Claude CodeCodexCursor +2
Sandbox workspace tools: search, file read, DB queries, integrations. Returns synthetic data. Remote server at vandorla.com.
not rated 0 1mo ago A
tokens not measured
original MIT
report-needs
70MCP server Claude CodeCodexCursor +2
MCP server for AI agents to report infrastructure needs they encounter. Runs locally from the report-needs Python package.
not rated 0 5mo ago A
tokens not measured
original MIT
gatekeeper
71MCP server Claude CodeCodexCursor +2
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit. Runs locally from the @runestone-labs/gatekeeper-mcp npm package. Needs 4 environment variables to run.
not rated 0 12d ago A
tokens not measured
original Apache-2.0
vigile-mcp
72MCP server Claude CodeCodexCursor +2
Query trust scores for MCP servers and agent skills. Check if a tool is safe. Runs locally from the vigile-mcp npm package.
not rated 0 5mo ago A
tokens not measured
original MIT archived
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: