Search

MCP server for RugSense — score freshly-launched Base tokens (rug/honeypot risk → AVOID/WATCH/HOT) over x402. Tools: get_base_launches, check_base_token, check_base_tokens_batch.

A lightweight MCP server for interactive user feedback via browser dialogs

A zero-dependency local API bridge for OpenAI & Anthropic. Accepts Chat Completions, Anthropic Messages, and OpenAI Responses formats, with prompt injection and prompt-cache keepalive.

Claude Code-native workflow distribution.

MCP server for Contextberg — query your activity tracking data, AI-generated daily/weekly reports, and Long-Term Memory from Claude Desktop, Codex, Cursor, and other MCP-compatible clients.

Claude Jar v2 — native desktop visual companion (Tauri + Svelte) with MCP/hook integration for live Claude activity. Beautiful accumulating jar + live intensity meter. The jar is the usage meter.

A real-time, provenance-invalidated cognitive cache layer for AI agents and RAG.

Claude Jar v2 — native desktop visual companion (Tauri + Svelte) with MCP/hook integration for live Claude activity. Beautiful accumulating jar + live intensity meter. The jar is the usage meter.

Local-first deep research: your models, your connection, your disk. Multiple local LLMs research the live web as independent analysts; a blind editor compiles a cited report.

Open, agent-agnostic MCP server that turns a spec (any SPEC.md, best with a PreCode .precode/ package) into a self-correcting, verified build. Drives a phased build → recheck → fix loop with hard definition-of-done gates and an implemented-vs-todo ledger.

AI proofreading for public web pages and full sites, with AI-verified corrections. Paid plans only.

Connect your wearables, rings and training apps, then ask your AI about your own health data.

Cross-venue prediction market routing for AI agents — arbitrage, quotes, and demand intelligence.

AI ops team for founders: approvals queue, inbox triage, briefing, follow-up drafting.

Register every AI agent, log every action, prove it. EU AI Act compliance built in.

N3MO: Code intelligence engine mapping repositories into queryable symbol graphs.

Manage clients, plans, sessions, habits, and billing on Trainzilla via one-click OAuth.

TypeScript runtime and CLI for connecting to configured Model Context Protocol servers.

Model Context Protocol server for Perkamo loyalty and gamification operations.

Real MCP server (JSON-RPC over stdio / Streamable HTTP) backed by sACP. Each tool call charges a prepaid credit balance and auto-funds + settles a sACP Job behind the scenes, so MCP hosts (Claude desktop, Claude.ai, ChatGPT) can call sACP-paid agents the