PreClick — An MCP-native URL preflight scanning service for autonomous agents (formerly URLCheck).
Verified · 37 days agoPreClick scans links for threats and confirms intent match with high accuracy before agents click.
PreClick scans links for threats and confirms intent match with high accuracy before agents click.
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale
Discover open-source AI agents and get source-owned installation instructions through MCP.
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
MCP server for CTFd v3: list challenges, submit flags, and query scoreboards via AI agents.
Fully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
Control Ableton Live from Claude, Cursor or Codex with LOM tools, device knowledge and recipes.
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
Run the validated Kshana PNT-resilience simulator (orbits, frames, GNSS, fusion) from an AI agent.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Govern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.
Privacy-first unofficial Polar AccessLink v4 MCP server for AI health, sleep and training agents.
Buy any of 24,000+ live x402 services with USDC on Base — the open marketplace for the agent economy
Expose deterministic ChainWeaver flows as MCP tools without LLM calls between steps.
MCP server: static security scanner for MCP servers, agent skills & plugins. 17 attack patterns.
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
Research Hadith, authenticity, grading, Takhrij and Sharh [commentaries] in Claude Desktop for free.
Compiles structured specs into SCORM 1.2/2004 e-learning packages. 43 tools, quality gate, no LLM.
Stateful Windows RPC attack-surface research for AI agents: 22 tools on NtObjectManager.
An open-source benchmark of how well LLMs solve nonogram puzzles, from 5x5 to 20x20.