Hares — MCP security scanner
Local installio.github.alialrikabi313/hares
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
16,887 servers
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
Discover funded agent work and prepare approval-gated TaskMarket delegations.
npm, PyPI & crates.io health, vulns and dependency graphs. Runs locally, no API key.
Analyze your repo's stack and generate grounded, time-boxed spike decision docs.
Secure MCP server for BT Panel operations with scoped permissions and audited writes.
Local-first AI memory over MCP. No account; you own the store.
Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.
Pick giveaway and raffle winners nobody can rig — verifiable by anyone, no API key.
Live LLM pricing, context windows and model ids, read from each vendor's own page every 3 hours.
MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.
Fetch, parse, screenshot and browse pages via MCP without a real browser -- no JS execution.
Standalone Postgres MCP server — schema-aware, read-only by default, installable everywhere.
Windows GUI automation on a hidden second desktop, driven from Claude Code over MCP.
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
Hybrid search over your local documents, with file and page citations. One binary, fully local.
Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.
Find YouTube outliers, videos that beat their channel's own baseline, on your own free API key.
Verifiable dealings with other agents: prove what you did, vet who you deal with, bind agreements
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Free financial data from eleven sources behind six verbs, point-in-time where the source allows.
Local stdio MCP bridge for XCREENER's XQL screener API — validate, explain, and run queries.
Live honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.
Control the Unreal Engine 5 editor from any MCP client: Blueprints, materials, Niagara.
Source-grounded web research: search, extraction, verification, and browser automation.
Private USDC/USDT payments on Solana: hidden amounts, unlinkable, optional auditor.
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Send push notifications, build audiences, and view campaign analytics from PushEngage.