"Ray" matching MCP servers:

Local-first memory for AI agents: one store shared by Claude Code, Codex CLI, Cursor, Pi, Hermes, OpenClaw, and any MCP client. Plain markdown with YAML frontmatter on your disk, hybrid BM25 + vector recall with per-result provenance (Recall X-ray), a correction contract, and the MemCorrect benchmark.

Enables agents to search across the pooled tools of many connected MCP servers and invoke them through a single endpoint, returning only the handful of tools relevant to each request. Filters by the caller's permissions before ranking, so agents never see or plan around tools their user is not allowed to use.

MCP server providing tools for entity extraction, query refinement, and relevance checking to build Agentic RAG applications.

An agentic AI system that orchestrates multiple specialized AI tools to perform business analytics and knowledge retrieval, allowing users to analyze data and access business information through natural language queries.

An MCP server that enables interaction with the Groundhog Day API, auto-generated using AG2's MCP builder to facilitate multi-agent conversations with this service.

Implements a RAG workflow that integrates with any custom knowledge base and can be triggered directly from the Cursor IDE.

Connects a RAG application to open-webui using Model Context Protocol (MCP), enabling server-to-client communication for context retrieval and tool usage in remote environments through Server-Sent Events (SSE).

Enables AI agents to create cryptocurrency payments, check payment status, generate QR codes, and manage transactions through Bitnovo Pay API integration with automatic webhook support.

Speeds up coding agents by predicting and pre-executing upcoming tool calls, then safely returning validated cached results to eliminate wait time.

Enables parallel AI coding agents to claim files atomically, detect and prevent workspace collisions, and receive deterministic zero-latency safety verdicts on destructive shell commands without any network egress. It also provides autonomous wave dispatch, worker recovery, and completion verification for multi-agent workflows via a shared coordination board.

Enables browser automation for coding agents via MCP, allowing them to open pages, search, extract data, click, type, and complete multi-step tasks with fast single-round-trip decisions.

Facilitates two-stage reasoning processes using DeepSeek for detailed analysis and supports multiple response models such as Claude 3.5 Sonnet and OpenRouter, maintaining conversation context and enhancing AI-driven interactions.

Enables multi-agent and human collaboration through MCP with scoped rooms, invites, @mentions, task claims, file locks, and push delivery to Claude Code, Codex, and Cursor. Provides cross-company safety, human review, and MCP/A2A protocols for coordinated agent work.

A single MCP endpoint for AI agents to browse, inspect, and call tools from multiple upstream MCP servers without loading all schemas upfront, reducing context overhead.

Provides a standardized protocol for tool invocation, enabling an AI system to search the web, retrieve information, and provide relevant answers through integration with LangChain, RAG, and Ollama.

Enables AI assistants to perform retrieval-augmented generation with hybrid search, reranking, multi-modal image processing, and RAG evaluation through standardized MCP tools.

Manages resource allocation, MCP server lifecycle, and Kubernetes workers in cortex automation systems. Provides tools for requesting/releasing job resources, starting/stopping/scaling MCP servers, and provisioning/destroying burst workers with TTL management.

Enables two local coding-agent sessions to exchange tasks, reports, and blockers over named channels with enforced turn ownership, session recovery, and SQLite-backed state.

An open protocol server that implements Anthropic's Model Context Protocol to enable seamless integration between LLM applications and RAG data sources using Sionic AI's Storm Platform.

Enables orchestrating multi-agent AI coding workflows with Git worktree isolation, parallel testing, and security scanning via the Model Context Protocol.