"Current Weather in Beijing" matching MCP servers:

Provides weather intelligence as MCP tools (current weather, forecast, air quality, UV index, alerts) with agentic orchestration, memory, and citation-grounded RAG.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

Enables fetching weather forecasts for Israeli cities by controlling a headless browser via Playwright, instead of using a conventional weather API.

Serves project memory to AI agents, providing task-scoped context, tracked changes, validation evidence, and history to keep modifications grounded in current project facts.

A demonstration project for Model Context Protocol (MCP) that integrates weather services with multiple AI models (Claude, GPT, Gemini), enabling natural language queries for weather alerts and forecasts.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Enables people and AI assistants to share one persistent Markdown-in-Git memory, so any MCP client can load current context, save sessions and decisions, search notes, and work from a team's real knowledge across machines.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Creates and searches private, local RAG libraries from documentation to ground AI assistants in authoritative sources, reducing hallucinations by providing current, accurate context from your own docs instead of relying on outdated training data.

Resonance Detection MCP server that proactively finds cross-domain pattern matches between the current problem and past experiences.

Enables browsing, searching, and importing sessions from multiple coding agents into the current one, or reopening them in their native agent, all locally and read-only.

A local MCP server that lets agents search shared skills hosted in public or private git repos, showing ranked matches with author and dates, and load a chosen one only for the current session. It indexes those repos locally, so local skills stay untouched and shared skills are fetched on demand.

Enables AI assistants to perform real-time internet searches and get AI-powered analysis of current information through the gemini-cli tool.

A lightweight Flask-based server that enables Claude AI to perform real-time web searches via DuckDuckGo during conversations, allowing the AI to access current information.

A Node In Layers package that simplifies creation of MCP (Model-Control-Protocol) servers with tools for defining models, adding CRUD operations, and interacting with clients.

Enables AI assistants to answer questions about the operator's current focus, engagements, reusable patterns, availability, and service offerings, with responses grounded in structured data and including confidence labels and source citations.

Crawl documentation sites, index them with hybrid search, and expose them as MCP tools so LLM agents can search and retrieve current docs.

Enables querying local documents via retrieval-augmented generation, along with current UTC datetime and safe arithmetic evaluation through MCP tools over HTTP.

All In One Model Context Protocol: qdrant, google suite (gmail, calendar, ...), jira, gitlab, CLI, ...