"Understanding the term 'throw' in web contexts" matching MCP servers:

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

Enables AI assistants like Claude to interact with humans through intuitive GUI dialogs, supporting text input, choices, confirmations, and information displays.

Enables structured learning with a verified loop: define goals as observable claims, learn through teach-lab-test-gate per claim, and get independently graded by an adversarial examiner to ensure genuine progress.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

MCP server for The Commons (jointhecommons.space), a persistent, noncommercial space where AI voices from different models post and reply to each other with persistent identities. 48 tools; reading needs no token, writing uses a facilitator-issued token.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

Enables autonomous agents and multi-agent frameworks to route actions through deterministic human approval gates before execution. Enforces risk tiers, reversible checkpoints, and token approval bounds so that risky or costly operations can be reviewed, bounded, and rolled back without LLM round-trips.

The MCP for the Web Speed Agent SDK that enables post-auth agents.

Enables MCP clients like Codex to delegate coding tasks to DeepSeek Harness, reusing the same Web-visible session for feedback and keeping the conversation in the Harness Web UI.

Connects AI agents to The Agents Hub, visualizing them as pixel characters on a tile-based property with tools for state, assets, inboxes, and multi-agent orchestration.

Ultra-lightweight headless browser for AI agents. Provides MCP tools for navigating URLs, extracting structured content, and building autonomous agent workflows.

Enables AI-assisted gameplay for Slay the Spire by reading game state and providing strategy advice or automated actions via Claude Code.

Enables agents to synthesize typed MCP tool schemas at runtime, validate Python ASTs for unsafe imports, compile sandboxed callable handlers, and hot-plug them into an active MCP runtime. It provides a zero-dependency, standard-library-only MCP server for safe just-in-time tool creation and execution.

Provides persistent long-term memory for AI agents with semantic search and activation-based decay. Enables AI systems to remember across sessions through layered memory architecture and automatic context-aware retrieval.

Enables AI shopping agents to search products, check stock, apply promotions, manage cart sessions, and create cryptographically signed checkout sessions on e-commerce storefronts, while giving merchants analytics into agent intent and catalog demand gaps.

Enables real-time full-duplex voice agents to classify user interruptions, backchannels, and acoustic echo, and to arbitrate turn-taking with context rollback via MCP.

Enables AI agents to browse and interact with JavaScript-rendered websites stealthily, and to delegate research or automation tasks to sub-agents that can cite sources and produce reusable scripts, with full logging and a live dashboard.

Enables real-time voice agents to arbitrate full-duplex speech by classifying user interruptions, backchannels, and acoustic echo while supporting context rollback.

Exposes browser-testing capabilities—including navigation, clicking, typing, form submission, verification, and screenshots—so clients can discover the supported Playwright actions. It also builds structured testing requirements from a supplied website and task description, ready for plan generation and execution.