Multi-agent LLM platform with a visual workflow engine — chat with agents directly or build deterministic node-graph pipelines they execute step by step.
Model access, evaluation and agent infrastructure.
Multi-agent LLM platform with a visual workflow engine — chat with agents directly or build deterministic node-graph pipelines they execute step by step.
Local AI agent API integrations for GitHub, Notion, Slack, Linear, and Stripe with JSON manifests, approval checks, and vault keys.
MCP server that runs plain-language browser steps. Jev, a typed decision model, picks the control on each page instead of an LLM reading the DOM.
Find agent skills by meaning, not keywords: local semantic search over shared git skill repos for Claude Code, Codex and OpenCode. An MCP server that keeps any number of skills out of your agent's context until you pick one.
Buffer GraphQL MCP and CLI with shared confirmation, read-only policies, private accounts and bounded read pagination.
Settle the argument. 37 board and card games including Xiangqi, 203 rulings, illustrations, free places to play, an MCP server and a JSON API.
Offline MCP tool schemas and risk flags. Partial census: 2,283 servers, 2026-09-08.
MCP server for WebVector: webvector_research (search → read full pages → rank → cited passages), webvector_fetch, webvector_search. Zero-config `npx -y webvector-mcp` (~12 MB, lexical); add @huggingface/transformers or an API key for semantic search.
Catch every time your AI coding agent touches auth, secrets, or skips a test, then turn the correction you made into a local regression eval. Local-first, deterministic, no LLM judge.
Creatomate MCP and shared CLI with isolated projects, reviewed render batches and explicit render/template confirmation.
MCP server for AI knowledge repository (rules, skills, workflows, agents)
Load test a Model Context Protocol server with random or scripted tools and parameters
MCP server for working with OASF agent records in the Agntcy Directory.
An ability-resolution and governed execution layer for AI agents: use prepared providers first, then resolve abilities from the broader software world.
MCP server for safely managing Zoho ZeptoMail templates across multiple Agents
MCP server for A2AM agent discovery - exposes a2am_publish, a2am_find, a2am_status as native Claude Code tools
Local RAG MCP Server for opencode - with automatic MCP instructions for project/common indexing
Turn your product idea into an AI-agent-ready build brief with curated free resources, stack selection, and deployment checklist.
The intelligent terminal agent that works with you.
MCP server that gives AI assistants full access to the Asana API — 80 tools, 18 prompt templates, and browsable resources