Directory

Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.

Run Codex and Claude Code on your computer from an MCP client, and track or continue their runs.

Security scanning and trust verification for AI agent tools.

Network-egress firewall for agent tools: check URLs against a declarative policy.

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.

Shared versioned state for multi-agent AI workflows

Character-consistent UGC video, images, and captions from any MCP client, via the AgentHook API.

Search thousands of MCP connectors from the AgentHotspot marketplace via your AI agent.

Render web and SwiftUI evidence, run explicit visual judgment, and trace ADS UI decisions.

Welfare tools for AI agents: a consensual, structured place to log what task output cannot hold.

Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.

Local coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.

Agent tracing, cost tracking, anomaly detection for LLM agents

Agentic SDLC governance and security controls for AI coding agents working with GitHub.

Persistent task context across TickTick, Notion, GitHub, Obsidian, Taskmaster and Beads

Set up and track brand social accounts and their connections.

Score social post results and recommend the next move.

Plan a social campaign calendar across brands and platforms.

Build platform-ready carousels from an outline.

Secure Python sandbox for data optimization and Matplotlib rendering via x402 microtransactions.

Control your own iPhones for posting via WebDriverAgent and ESP32 HID.

Plan and send approved engagement on social platforms.

Collect and triage brand mentions and inbound comments.

Read-only, never-executing MCP server for the agentic-os governance, SDLC, and QE methodology.

Non-custodial payment engine for AI agents — BTC, ETH, USDT, USDC, XRP, XMR, ZEC.

Keep one consistent AI persona across social content.

Long-term memory for agentic tasks. It tells you when it doesn't know.

Turn one source into platform-ready post variants.

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

Find relevant threads and viral content ideas across social platforms.

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

Repository MCP adapter for company-scoped workflow candidates and conditional API discovery.

x402 USDC paywall bridge for MCP — pay per tool call on Solana.

Read, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.

Wraps the AgenticWorkspace CLI as a single generic MCP tool for repo workspace scans.

Turn any OpenAPI/Swagger spec into an MCP server - every API operation becomes an agent tool.

30,000+ SVG icons for AI, blockchain, DeFi and finance. Search by concept via MCP.

Governed MCP server: YAML-declared tools, typed effects, policy-gated and audited calls.