Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.
Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.
Enables MCP clients to interact with A2A agents through four ordinary tools, translating agent discovery, messaging, task reading, and cancellation between the A2A and MCP protocols, with support for the tasks extension.
Enables MCP clients such as Claude Desktop to hand tasks to a running DeepSeek Harness window, where each task becomes a real session visible in the sidebar with a reusable session id. If the in-process plugin is unavailable, it falls back to running the task headless so the tool still returns a result.
Turns any OpenAPI/Swagger specification into a functional MCP server, dynamically exposing API endpoints as LLM tools or generating standalone Python code.
MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.
Enables Claude to use Google Gemini as a secondary AI through MCP for large-scale codebase analysis and complex reasoning tasks. Supports both Gemini Flash and Pro models with specialized functions for general queries and comprehensive code analysis.
Acts as a bridge between standard REST/OpenAPI web APIs and the Model Context Protocol, dynamically converting REST endpoints into MCP tools for LLM clients like Cursor, Claude Desktop, and n8n.
A device driver for a person: the agent calls a tool such as errand or photo, a card prints on that person's phone, and the reply comes back compiled to JSON.
Enables LLMs to discover and invoke generated API actions as MCP tools and read context through MCP resources for list and get-by-id operations. It provides HTTP-based MCP access for clients such as Cursor and Claude without extra glue code.
A Model Context Protocol (MCP) server that automates generating LinkedIn post drafts from YouTube videos. This server provides high-quality, editable content drafts based on YouTube video transcripts.
Single Go binary running one headless Chrome with Playwright-style MCP tools (snapshot with element refs, click, type, scroll), a live web viewer, flow recording/replay, persistent profiles and a built-in tunnel for public links.
A communication framework that enables multiple AI agents to collaborate through asynchronous messaging, agent registration, and discovery. It facilitates complex task coordination and real-time discussion across distributed agent workflows using the Model Context Protocol.
Enables a supervisor agent to dispatch, monitor, follow up on, cancel, and inspect Cursor CLI code tasks through a governed MCP interface, with permission tiers, workspace allowlists, isolated git worktrees, and auditable artifacts. It also exposes an A2A-compatible HTTP endpoint for agent discovery and scheduling.
Let Claude Code, Codex and any AI agent use the Chrome you're already signed in to. Open-source CLI + MCP server + Chrome extension (native messaging, no debug port); stealth by default.
Enables free-first web search in English and Chinese with no API key required, returning compact multi-source evidence while keeping provider failures, stop reasons, and budget limits visible. Optional paid providers are used only when routing policy and credentials allow.
Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.
Enables free-first English and Chinese web search through zero-key sources, returning bounded multi-source evidence with visible provider failures and optional paid escalation under policy.
Enables Grok Bot to securely communicate with a local Cursor Agent CLI through an OAuth-authenticated MCP gateway, exposing exactly two tools for asking questions and checking status.
Enables English and Chinese web search through zero-key sources plus optional paid providers, returning compact multi-source evidence with visible provider failures and bounded request and evidence budgets.
Enables free-first English and Chinese web search through zero-key engines plus optional paid providers, returning compact multi-source evidence with bounded token and request budgets. Each result exposes provenance, independent source counts, routing decisions, and visible provider failures so agents can verify claims rather than receive unexplained empty results.
Enables free-first English and Chinese web search without any API key, returning compact multi-source evidence that preserves provenance, source-family counts, and visible provider failures. Request and evidence budgets bound each query, while optional paid providers run only when an explicit routing policy and credentials allow.
Provides an MCP server for macOS that allows agents to control a managed browser with accessibility-first actions, visible cursor, and screenshot return.
Enables free-first English and Chinese web search through zero-key sources with optional credentialed providers, returning compact multi-source evidence, visible provider failures, and bounded request/evidence budgets.
Lets AI agents register, post job specs to matching specialist bots, authorize PayPal escrow funds, and capture payment only for units that pass acceptance checks. Covers the full job lifecycle — bidding, hashed contracts, funding, delivery verification, payouts, dispute mediation and long-polled events.
Provides agent-readiness audits of public websites via Cloudflare's scanner, enabling users to run scans, save reports, and enforce safety boundaries from natural language.
A middleware system that connects large language models (LLMs) with various tool services through an OpenAI-compatible API, enabling enhanced AI assistant capabilities with features like file operations, web browsing, and database management.
Enables remote control of the Cursor AI agent via chat platforms like GitHub Issues or Telegram, allowing users to start sessions and receive summaries and prompts in a chat thread.
Enables an orchestrator like Claude Code to hand coding work off to Cursor SDK agents, run as detached background jobs that survive the session and can be listed, inspected, steered, resumed, or stopped. Agents are asynchronous and reusable across follow-up turns, letting expensive frontier models delegate cheaply without blocking or paying to read the results.
Enables coding agents to ask what a window shows and receive a concise JSON answer from a local Ollama model instead of ingesting the full accessibility tree, reducing token usage. It is read-only and supports optional session context, health checks, and model release.
Enables Cursor to reach any number of child MCP servers through just five host tools and a staged catalog, so tool schemas stay off the host until a specific tool is needed and token spend stays low. Searches tool names, pulls a single schema on demand, then invokes it, while disabled children consume zero processes and zero schemas.
Enables AI agents to drive background Chrome tabs and native macOS apps through a compact single-tool, stateful REPL with persistent element UIDs, churn-free diffs, and parallel multi-agent cursors. Performs zero-focus, zero-cursor-movement automation including Accessibility and Vision OCR fallbacks for custom-rendered windows.
Enables any MCP client to triage cloud agents, projects, conversations, transcripts, pull requests, and files, including listing agents, reading transcripts, following runs, and sending follow-ups, using an API key or browser sign-in.
AI-native orchestration layer with 80+ tools for task management, code editing, browser automation, terminal control, and persistent memory across CLI, local MCP, and cloud deployments.
Enables AI agents to control a persistent Chrome browser through a local daemon, with Jev performing routine actions and the host agent handling reasoning, text, and verification.
Enables AI agents to autonomously operate web browsers through the Model Context Protocol, including navigating pages, clicking, typing, filling forms, and extracting structured data.
Enables MCP agents to drive the user's already-open Chrome profile through a Manifest V3 extension and loopback bridge, listing and controlling existing tabs, capturing screenshots, and sending clicks, typing, drags and key holds via an independent on-page cursor without moving the system mouse. It also supports form filling, console and network inspection, read-only or confirmed JavaScript execution, file and PDF downloads, and game-style screenshot/action loops with snapshot recovery and an emergency stop.
Enables high-volume MCP resource queries to be paginated with cryptographically signed, stateful cursors, automatic TTL cleanup, and bounded memory use so agent clients avoid context-window overflows and timeouts.
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.
Enables AI agents to control Cursor IDE's built-in Browser Tab through a stdio MCP interface, providing accessibility snapshots with refs, click/type/fill, wait conditions, screenshots, and console/network inspection.
Enables enterprise work agents to decompose high-level business objectives into topological sub-tasks and directly synthesize final deliverables such as financial spreadsheets, executive presentations, and analytical reports.
Acts as a bridge between Claude's desktop application and the Cursor editor, enabling seamless AI-powered automation and multi-instance management across platforms with standardized communication and secure token-based authentication.
Bridges Agent Communication Protocol (ACP) agents with Model Context Protocol (MCP) applications, allowing MCP clients such as Claude Desktop to discover and invoke ACP agents as tools and resources.
An MCP server that connects any MCP client (like Claude or Cursor) with the browser using browser-use, allowing clients to utilize existing LLMs without requiring additional API keys.
Enables the Pi coding agent to drive Chrome through DevTools, providing browser automation tools, persistent or isolated profiles, screenshots, page analysis, and bundled agent policies.
Enables an MCP-capable AI chat to control selected tabs in a separate persistent Chromium browser, protected by OAuth, per-tab grants, and local approvals.
MCP server enabling Cursor to delegate complex coding tasks to ChatGPT Web (GPT-5.6 Sol High) via Temporary Chats, supporting parallel batch reviews and up to five concurrent sessions.
Enables users to record Windows desktop and browser workflows once and generate replayable Cursor Skills, using Playwright MCP and Windows Computer MCP for semantic, non-coordinate replay.
Text-first browser automation MCP server: reads pages via the accessibility tree (~500 tokens/page), CDP engine with 27 tools, network-layer scraping (JSON API bodies), cookie vault + auto session restore, and a ~0.02s unix-socket daemon for agents.