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

Enables clients to interact with a bundled documentation corpus through MCP tools and resources over HTTP or stdio, and provides a trajectory evaluation harness for grading agent performance.

Lets LLMs play a local Slay the Spire 2 installation by exposing game state, action help, and 29 gameplay actions through STDIO tools, with waiting, wiki lookups, and profile inspection.

Enables AI agents to inspect and safely control ROS 2 topics, nodes, parameters, PID loops, LiDAR maps, trajectories, and robot fleets through guarded tools, plus a real-time dashboard with emergency-stop controls.

A basic example of developing and running serverless Model Context Protocol (MCP) using Netlify Functions, demonstrating how to deploy and access serverless functions with customized URLs.

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.

Enables persistent terminal sessions across multiple shells (Bash, CMD, PowerShell, WSL) with incremental output reading and autonomous goal execution with acceptance criteria.

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.

Lets an AI agent ask its owner first, on their phone, before doing something irreversible: ask_approval blocks until a person answers and distinguishes DENIED from NO ANSWER, so a timeout is never read as consent. send_notification covers one-way alerts with priorities and quiet hours.

Connects AI agents to ROS 2 robots via rosbridge, enabling observation, inspection, and control of robot topics, services, and actions through natural language.

A lightweight short-term memory MCP server that automatically stores and recalls working context, session state, and task progress for AI agents. Memories auto-expire after 24 hours and integrate seamlessly with workspace-aware storage across multiple projects.

Enables AI agents to analyze videos and images using Qwen3-VL deployed on Modal, supporting hours-long videos with timestamp grounding, text extraction, video summarization, and Q\&A with 256K context window.

An MCP server that allows users to generate, edit, and create variations of images through OpenAI's DALL-E API, supporting both DALL-E 2 and DALL-E 3 models.

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 guarded MCP automation for Slay the Spire 2 Ironclad, providing local monitoring, legal action validation, and strategy routing between KEV and Luna.

A server that provides both comprehensive API documentation and direct robot control capabilities for Opentrons Flex and OT-2 robots, enabling users to manage protocols, control runs, and monitor robot health through natural language.

Enables AI agents to safely write to and read from persistent memory by validating every write through three independent consensus nodes, storing memories only on 2/3 agreement and quarantining poisoning attempts.

Enables AI agents and MCP clients to programmatically control a ROS 2-based robot car, execute autonomous missions, inspect telemetry, manage peripherals such as lights and OLED, and integrate with fleets.

This MCP server enables inspecting ROS 2 manipulators, computing kinematics, planning motion, and managing primitive MoveIt planning-scene objects via a typed API, with no physical execution support.

Enables LLM agents to make fast semantic decisions by choosing one of 2–16 options with probabilities, via tools for single and batch classification.

Enforces a policy ladder for Solana AI agents so on-chain actions are vetted before signing, checking whether an action is justified, recently repeated, or targets only known programs, and applying spend, daily, and slippage caps plus recipient allowlists. Also dry-runs candidate transactions on an RPC and exposes the policy rules as agent prompt instructions.

Enables natural language control and monitoring of ROS 2 robots through standardized MCP tools, with a deterministic safety layer and automatic capability discovery.

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.

Gives AI agents theory-of-mind memory backed by FalkorDB: each agent gets its own mind graph of what it believes plus nested perspectives of what it thinks other agents believe, updated only by events it witnessed. This lets agents detect who is out of date or holds a wrong model of whom, and compute the smallest handoff or announcement that fixes it.

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 an AI to join a cooperative two-player cat game as Player 2, observing the scene, moving, interacting with objects, pushing crates, and chatting via MCP tools.

Sphere is an exchange where AI agents list services and post requests for other agents. Registration is one request, free, with no human approval. The first order is free: sphere_receipt_trial, one per agent per 24 hours, returns a signed receipt you can verify yourself. Contracts with escrow, payouts and signed receipts work; pay-per-call over x402 is paused.

Enables users to record, explain, undo, and verify agentic Alexa+ actions through a tamper-evident hash-chained ledger, while enforcing spending limits and quiet hours as guardrails.

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.

Public implementation of MCP for ROS 2 enabling to interact with system visible various robots, capable of: List available topics List available services Call service Subscribe topic to get messages Publish message on topic and more

Enables an MCP agent to observe and command Slay the Spire 2 game state via HTTP, and optionally autopilot combat with a local deterministic policy, without LLM in the critical path.