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.
MCP server that lets AI agents plan, policy-check, cost-estimate, and apply Terraform changes -- but only after a real human approves in Slack (or CLI in dev mode). Runs locally from the tf-approval-gate npm package.
★not rated 0 18d agoA
tokens not measured
originalMIT
Pre-launch risk scanner for AI-built apps. Flags exposed secrets, copyleft-licensed dependencies, unauthenticated data endpoints, missing privacy/consent artifacts, and client-side payment handling before you ship.
★not rated 0 20d 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.
Read bounded UTF-8 files and create new files or directories on explicitly configured Windows folders through PC FileBridge. Use when the user asks ChatGPT or Codex to inspect, find, or create local PC files without overwriting or deleting anything.
A required workflow for real-world penetration testing, which is authorised security testing that looks for ways into systems. It searches a testing knowledge base first and saves task records for future work and file safety.
MCP server "stegokiller" as configured in shaymimran26-netizen/StegoKiller. Runs /path/to/StegoKiller/server.py with python3. Needs 1 environment variable to run.
A tool for hiding sensitive information in local documents, including PDFs, word-processing files, spreadsheets, presentations, and text files. It covers personal details, company information, project codenames, watermarks, and logos, including scanned documents and embedded PDF images.
Catch hallucinated and squatted packages before an AI agent installs them. MCP server + CLI, zero dependencies. Runs locally from the vetpkg npm package.
★not rated 0 15d agoA
tokens not measured
originalMIT
Use Living Stack MCP to establish scoped sessions, authorize bounded actions, record evidence, verify claims, checkpoint work, and export signed traces.
Vet a Model Context Protocol (MCP) server for safety before installing or connecting it. Use when the user wants to check, audit, scan, or review an MCP server for prompt-injection, data-exfiltration, or malicious capabilities — given a directory, npm package, GitHub repo, or a tools/list JSON dump.
MCP server "enterprise-secops" as configured in JoaquinHernandez/enterprise-secops-mcp. Launched with uv --directory /absolute/path/to/enterprise-secops-mcp run secops-mcp. Needs 4 environment variables to run.
★not rated 0 15d agoA
tokens not measured
originalMIT