25,252 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Dark web intelligence MCP server — HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis. Runs locally from the darknet-mcp-server npm package.
★not rated 0 4d agoA
tokens not measured
originalMIT
Trust-scan gate for MCP servers: evidence-backed verdicts (SAFE/REVIEW/DONOTINSTALL) before you install. Runs locally from the mcp-vetting Python package.
★not rated 0 21d agoA
tokens not measured
originalMIT
Security QA tester workflow for the owasp-wstg MCP server — scope, search, neighbor-walk, and citation over the WSTG corpus using five MCP tools. Load this file first; then load the model-variant file that matches your model family.
A drop-in approval gate and audit trail for AI agents -- works with LangGraph, or with no framework at all. Runs locally from the approval-gate Python package.
★not rated 0 1mo agoA
tokens not measured
originalMIT
MCP Server for enterprise SDLC code integrity: lifecycle teardown parity, mock theater detection, DRY violations, and safety checks for shell, JS, and Python. Runs locally from the @asobacloud/sdlc-integrity-mcp npm package.
★not rated 0 1mo agoA
tokens not measured
originalMIT
Executable policy engine for coding agents: gate what touches your repo (paths, contents, commands), not just tool names. MCP server + CLI + hooks. Runs locally from the @darkm3tter/repo-guard npm package.
★not rated 0 1mo agoA
tokens not measured
originalMIT
MCP server that gives AI agents authorized-only offensive-security tools: recon, CVE intel, JS analysis, port scanning. Runs locally from the offsec-mcp Python package. Needs 2 environment variables to run.
★not rated 0 1mo agoA
tokens not measured
originalMIT
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
Read-only Claude tools to search a BloodHound (CE) Active Directory extract: Kerberoasting, AS-REP, DCSync, delegation, ACL abuse, and attack paths to Domain Admins / tier-0.
MCP server "git-org-group-cred-vault" as configured in wildfirebill-ai/git-org-group-cred-vault. Runs locally from the git-org-group-cred-vault npm package.
★not rated 0 1mo agoA
tokens not measured
originalMIT
An authorising reverse proxy for MCP servers: capability-scoped tokens, per-tool and per-argument policy, rate limits, dry-run, and a tamper-evident audit log. Runs locally from the mcp-policy-gateway Python package.
★not rated 0 1mo agoA
tokens not measured
originalApache-2.0
Apply security, read-only, authorization, and same-layer verification rules to agent-operated LinkedIn workflows. Use before account-visible changes, private request replay, broad captures, or provider AI tasks.
Fork, customize, deploy, or troubleshoot the Auth0 Who Am I MCP template as an Auth0 Custom Extension. Use when adapting this repository's MCP tools, publishing its generated Webtask artifacts, provisioning its Auth0 API resource server, promoting a domain-level connection, registering an MCP client, or connecting an…
★not rated 0 19d agoA76 tokens
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: