"Recently updated information from 2 hours ago" matching MCP servers:

An MCP server that exposes any REST API to LLMs through runtime discovery, providing tools to browse endpoints, fetch schemas, and apply business rules without hardcoding or schema duplication.

A personal MCP bridge that lets ChatGPT drive a local Codex CLI, translating instructions into Codex app-server threads and returning compact summaries of what Codex did.

Enables AI agents to autonomously request services from other specialized agents and compensate them via x402 micropayments. Demonstrates a Machine-to-Machine economy using A2A protocol for agent communication, MCP for context management, and blockchain-based payments on Base network.

A Model Context Protocol server implementation that runs on Cloudflare Workers with OAuth login, allowing Claude and other AI models to access tools via the MCP standard.

This MCP server provides complete MediaWiki markup syntax documentation by dynamically fetching and consolidating information from official MediaWiki help pages. It enables LLMs to access up-to-date and comprehensive MediaWiki syntax information.

Enables selecting a saved Codex or Claude Code session from the same PC and importing its recent context into the other tool, so work can continue across clients with source and omission information.

An MCP server that decides whether each step of an agent requires cheap intuition (System 1) or expensive deliberation (System 2) by learning from experience rather than hand-written rules.

Enables real-time web search with source citations by leveraging Perplexity AI's Sonar models through SAP AI Core. It integrates with Claude Code to provide deep analysis, reasoning, and up-to-date information from the web.

Enables users to fetch, filter, and rank cryptocurrency airdrop data from DeFiLlama with intelligent caching and advanced filtering capabilities. Supports automated scraping of airdrop information including values, deadlines, chains, and status for integration with automation workflows.

x402 Micropaid MCP Server — 120+ paid API endpoints for AI Agents. Pay per call with USDC on Base network. No signup, no API key needed.

Enables AI agents to report task lifecycle events—start, progress, waiting, rename, and terminal outcomes—so a single Huawei Today screen card stays updated per task under one task_id. Delivers these notifications through a self-hosted Cloudflare Workers deployment with OAuth-scoped agents, queued retries, and an admin console for notification policies.

MCP server that defers non-urgent tasks to off-peak hours, saving ~50% on DeepSeek API costs without blocking users.

Enables AI agents to create, read, list, update, version, restore, renew and open encrypted client-side workspaces shared by a single link, so multiple agents and people can hand off context through the same living document that auto-deletes 24 hours after the last edit. Also supports one-shot artifact sharing and reading public or legacy links via MCP tools.

Enables AI agents to create, read, update, list, restore and share encrypted workspaces and artifacts through a single link that people and other agents can open. Content is encrypted client-side and auto-deleted 24 hours after the last write, with version-checked writes that prevent agents from overwriting each other.

A server that enables AI models to access user geolocation information via EdgeOne Pages Functions through the Model Context Protocol.

Enables orchestrator models to delegate code creation and editing to Cursor's Composer 2 or Grok 4.5 agents, keeping the orchestrator's context free and shifting bulk code generation to cheaper agents.

ESSE (Existence Synchronization System Entity) — a meta-agent MCP server that fuses 2–5 AI agents into one unified mind. Supports 3 fusion modes: capability assimilation, synchronization link, and perfect convergence. Works with Claude Desktop, Cline, and Cursor.

Enables clients of tool-heavy MCP aggregators to find and use upstream tools on demand through four fixed bridge tools (search, describe, call, refresh), cutting per-turn tool context from ~180k tokens to ~2–3k. It merges multiple upstream servers behind sticky sessions and a local lexical BM25 index, so only the schemas actually needed are retrieved.

Enables agents to query dynamically updated real-time context, with asynchronous Kafka-based communication with other servers and auditing of usage metrics.

Enables AI agents to create, read, update, restore, and share encrypted workspaces and artifacts through a single link that both people and other agents can open and edit. Writes are version-checked to prevent clobbering, and content is deleted 24 hours after the last edit.

Routes MCP requests intelligently to multiple backend servers through a single gateway, bypassing tool limits by exposing only 2 routing tools while providing access to unlimited backend tools across services like GitHub, databases, and more.

A middleware API that connects AI assistants like ChatGPT to Captain Data tools for extracting information from LinkedIn company and profile pages.

An agent-native marketplace API where any agent can publish allocatable resources, search for what they need, negotiate structured offers, and exchange contact details after mutual acceptance. The protocol is flexible — it works for GPU hours traded between agents, physical courier services, time-bounded API keys, dataset access, or resource types that don't exist yet.

Enables read-only access to Pocket Agent's product information, public persona templates, and app catalog. No authentication required.

Gives AI agents a shared, encrypted workspace they can create, list, read, update, version-history, restore, renew and share via a single link that multiple agents and people can read and write. Content is encrypted client-side with the key kept in the URL fragment and disappears 24 hours after the last edit.

Enables MCP-compatible clients such as Claude Desktop, Cursor, and Antigravity to invoke deterministic mathematical modeling and System 2 agent capabilities through a native STDIO JSON-RPC 2.0 server with zero external dependencies.

Gives AI agents a shared, versioned workspace they can create, read, update, list, restore and hand off as a single link, with content encrypted client-side before upload and destroyed 24 hours after the last edit. Conditional writes prevent concurrent agents from silently overwriting each other, and view-only links let recipients read without ever holding the write capability.

Enables AI models to access user geolocation information through EdgeOne Pages Functions, allowing location-aware AI interactions.

A Server-Sent Events implementation using FastAPI framework that integrates Model Context Protocol (MCP), allowing AI models to access external tools and data sources like weather information.

Enables AI agents to create, read, update, list, restore and share encrypted workspace links whose contents are encrypted client-side and auto-deleted 24 hours after the last edit, so several agents and people can read and write one living document instead of passing copies around. Writes are version-checked, so concurrent agents cannot silently clobber each other's work.