The Typescript MCP Framework
#claude
1913 posts
Security-first, self-hosted AI agents - isolation you can prove, not just promise.
Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.
MCP Server for use with ember projects
MCP server and plugin for Sperax Protocol – USDs, SPA, veSPA & Demeter on Arbitrum and BNB Chain. Listed on Anthropic's official MCP Registr...
A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing p...
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, G...
Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Pl...
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.
Pipedrive CRM MCP server for AI assistants like Claude — 300+ tools covering the full Pipedrive API. Built by Nubiia.
Natural Context Provider (NCP). Your MCPs, supercharged. Find any tool instantly, load on demand, run on schedule, ready for any client. S...