"Ray" matching MCP servers:

Lets AI agents send notifications, manage templates and read delivery status.

Enables governance-grade AIops for GPU inference clusters with root-cause analysis, metrics, and policy-governed operations for vLLM and Ray.

Local repo-intelligence MCP for coding agents: indexes source, symbols, call graphs, git/GitHub history, and source-bound repo memories into local database.

Enables command palette argument parsing and deep-link shortcut dispatch for Raycast/Alfred, allowing developers to route command invocations and execute keyboard-first productivity workflows through MCP.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Local-first agent memory & knowledge service: hybrid retrieval (vector + BM25/RRF) + memory governance (decay, dedup, freshness), REST + MCP dual protocol, fully offline without LLM. Python.

MCP server for GitHub code retrieval and reuse, using SQLite+FTS5 indexing and search history to enable search-first, requirements-refined code search from GitHub repositories.

Safe write access for AI agents. Stellar Jay is an append-only business fact store: every change is kept, attributed to the agent that made it, and can be undone. Agents record, correct and retract facts, read entities, and reverse a bad run with undo_changes. Self-host with stellarjay-mcp (Go, AGPL) or connect to the hosted AvianSuite server at https://mcp.aviansuite.com/mcp.

Universal CLI and MCP server providing unified payment links, customer prefilling, expiring checkouts, refund management, fee comparison, and HMAC-verified webhook proxying across Stripe, Razorpay, and LemonSqueezy.

Self-custodied Nano wallet + x402 payment client and merchant server for AI agents, enabling micropayments, on-ledger settlement, and paid endpoints.

Keyless local RAG over your own documents (ChromaDB) with traceable citations, exposed as MCP tools and a FastAPI endpoint.

Enables creation and management of academic-paper knowledge bases from PDFs, including ingestion, semantic search with reranking, and document-level retrieval via MCP tools.

"primitive" RAG-like web search model context protocol server that runs locally. ✨ no APIs ✨

Universal HTTP 402 Micropayment Protocol & Autonomous Economic Settlement Engine for AI Agents on Base L2.

Provides local hybrid search over files by combining semantic vector and full-text BM25 retrieval, with MCP stdio/HTTP support, OAuth 2.1 authentication, and tools for reading and converting documents to Markdown.

Deterministic Web3 x402 Critical Minerals, Battery Passport & Urban Mining Oracle. Delivers real-time LME/COMEX spot benchmarks, EUDR satellite audit, and sub-second 0.4s micro-settlements across Solana & EVM (USDC).

A comprehensive Model Context Protocol (MCP) server that exposes 216 tools, 7 resources, and 10 runbook prompts for every OpenShift 4 cluster operation an SRE, developer, or operator could need — all driven by an LLM.

A local-first RAG engine that ingests documents (PDF, Markdown, images, etc.) and provides hybrid search, reranking, and LLM answer synthesis via MCP for AI agent integration.

Lets AI agents search a marketplace of agent services, read seller storefronts, and prepare a checkout link that a human owner approves and pays in their browser. The agent never holds keys or signs.