27,008 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.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 169 tokens together
Pay-per-call network, domain, web and inference lookups for agents — DNS, SSL, WHOIS, IP reputation, email verification, web fetch & search, OpenAI-compatible gateway, embeddings, market data — in USDC over x402. No API keys, and the plugin never holds a key or signs a payment: each paid call is handed, with its exact.
MCP server Claude CodeCodexCursor +2
MCP server exposing cQnce human-in-the-loop authorization as AI-callable tools. Runs locally from the @cqnce/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Scans the code for security leaks. Runs locally from the codescan Python package.
8dp6brm9hp-svg/lion-mcp-public
Skill Claude CodeCodex
Before your agent sends USDC to an x402 payTo, screen that address with LION's $0.001 OFAC wallet screen. PASS proceeds. WARN or BLOCK aborts. The same wallet again is the $0.01 recheck. GO proceeds. HOLD or STOP aborts.
Plugin Claude Code
Bundles 21 skills, 1 MCP server · 1,341 tokens together
Centia BaaS for Claude Code: the Centia MCP server (tools generated from the Centia OpenAPI spec) plus skills covering runtime SDK usage, provisioning, JSON-RPC, auth, OGC/OWS services, snapshots, scheduler, realtime and delivery rules.
Cursor rule Cursor
DeterminAgents audit harnesses — apply when the user asks for a code audit, security review, test-gap analysis, or autonomous completion loop.
MCP server Gemini CLI
MCP server "burp-suite", hosted remotely at 127.0.0.1, as configured in legendwon/cau-eclass-mcp.
Plugin Gemini CLI
Check domains, links and IP addresses from public data: security score, phishing signals, DNS, TLS, email authentication and change history.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 82 tokens together
Look up CVEs (NVD) and scan packages and dependency files for known vulnerabilities (OSV.dev).
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 183 tokens together
Redact or anonymize PDFs, scans and screenshots on your machine before an AI or anyone else sees them. Black boxes, or consistent [Person 1] tags that keep the document readable, with the real names put back locally afterwards.
Skill Claude CodeCodex
Fetch public web pages safely through the safe-fetch MCP server's fetchurl tool. Use whenever you need the content of a URL (docs, articles, READMEs, feeds, JSON APIs). Covers paging long pages, handling refusals and errors, and treating fetched text as untrusted data.
Skill Claude CodeCodex
Develop and maintain the ArchiveBox connector while preserving its governed API actions, web-source contract, credential boundary, package resources, and public-first release evidence.
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 99 tokens together
Let AI agents operate your infrastructure under your control. Connects the agent to Alpacon, which checks each command at runtime, holds risky ones for human approval, and records them for audit. A bundled skill and hook keep the agent on Alpacon's MCP tools.
Plugin Claude Code
A signed receipt for every file edit, file write, notebook edit and shell command Claude Code makes, and a summary when the session ends. Hashes only: no commands, file contents or output.
jamesdfinance-dev/lazaretto-mcp
Plugin Cursor
Check a package, MCP server or agent skill before your agent installs it: free lockfile malware check, known-bad lookups, and a finder for MCP servers.
Little-H-lying-flat/72stack-sec
Skill Claude CodeCodex
A Chinese-language workflow for authorized security testing and bug bounty work, where researchers look for and report vulnerabilities in websites, applications, and cloud systems.
Plugin Claude Code
Bundles 1 command, 1 MCP server · 21 tokens together
Deterministic repository oracle for AI agents: point it at a repo and get one JSON answer — inventory, dependency graph, per-file risk, and the frontend-call x backend-route join — byte-identical for the same input, with its blind spots named rather than guessed past. TypeScript/JavaScript, Python, Java, C#, Rust, Go.
Agent Claude Code
Logic-bug and vulnerability hunter for the current diff. Use for /hunter, a security pass, or review before a PR. Not for docs or formatting.
Skill Claude CodeCodex
Onchain security scanner on Robinhood Chain — scan token approvals, detect honeypots, analyze contracts for rugpull indicators, check liquidity locks, and score contract safety. Use when a user asks an agent to evaluate, scan, or check a token or wallet before trading, swapping, signing an approval, or investing. 18…
Guruprasath-Annadurai/Whitepact
MCP server Claude CodeCodexCursor +2
ResponsibleAI — Enterprise AI Governance Platform: trust scoring, bias detection, hallucination detection, guardrails, compliance (NIST AI RMF / EU AI Act / ISO 42001), cost intelligence, drift monitoring. Runs locally from the rai-governance-platform Python package. Needs 1 environment variable to run.
Skill Claude CodeCodex
Discover x402 callables then check the seller BEFORE paying. Free resource join (GET /v1/intel/resources) lists listed|live402 claims; free preflight returns a ReadinessCard (allow / warn / block) from the observed Solana and Base x402 corpus. Composes with any x402 payer skill: discover → merchantcard wash refuse →…
MCP server Claude CodeCodexCursor +2
Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default. Runs locally from the altweb-context npm package. Needs 1 environment variable to run.
didvc/claude-email-leak-notice
Plugin Claude Code
Claude Code injects your account email into session context, where an agent may reuse it as a legitimate value and commit it. This warns once per session when a personal address appears in a tool payload. Never blocks.
drewrukin/llm-code-security-review-mcp
MCP server Claude CodeCodexCursor +2
MCP server "llm-code-security-review-mcp" as configured in drewrukin/llm-code-security-review-mcp. Runs locally from the llm-code-security-review-mcp Python package.
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: