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.
Enables any MCP client to browse, triage, search, read, and drive pi coding agent sessions through Pi Web's HTTP API via 25 tools. Supports listing and filtering sessions, reading transcripts, flagging conversations awaiting input, sending messages and waiting for replies, inspecting project diffs, and forking, renaming, or deleting sessions over either stdio or Streamable HTTP.
A Node.js application that connects WhatsApp Web with AI models through the Model Context Protocol, enabling automated messaging, contact management, and group chat functionality through AI-driven workflows.
A language-neutral runtime for the SEP-2663 task lifecycle and io.sdar/taskExecution Provider Profile, delegating resource facts and side effects to versioned gRPC/Protobuf adapters. Implemented in strict TypeScript, it provides durable scheduling, recovery, and a full test suite for conformance.
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 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.
Allows AI agents to control and interact with VS Code webviews by providing tools for navigation, element interaction, and state retrieval. It facilitates automated tasks like clicking elements, inputting text, and reading the DOM structure within a VS Code tab.
Ultra-lightweight headless browser for AI agents. Provides MCP tools for navigating URLs, extracting structured content, and building autonomous agent workflows.
Enables autonomous web automation by flattening DOM trees into pruned accessibility trees, synthesizing robust CSS/XPath locators, and compiling goal-driven multi-step action plans with verification. It exposes these capabilities through MCP JSON-RPC tools for browser-oriented task execution.
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.
This MCP server enables users to convert web page DOM structures into accessibility trees, filter non-interactive elements, generate robust CSS/XPath locators, and compile goal-driven multi-step browser automation plans with verification.
A multi-agent research system that decomposes complex queries into targeted sub-questions, searches the web in parallel, scores source credibility, and synthesizes findings into structured markdown reports.
Enables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.
Universal MCP server for WAIS (Web Agent Interaction Standard) that provides 5 generic tools to discover, register, execute actions, confirm high-risk actions, and check status on any WAIS-compatible site.
MCP server that delivers cross-platform identity and visual styling for AI agents — one bling.json, many surfaces (Claude Code, Claude Desktop, terminal, web, Slack, Discord, IDE). Includes WOW (Weird Office Workers), a random-identity generator with 13 weighted trait pools (465 entries), five rarity tiers calibrated against a 10k-roll empirical distribution, and HOMUNCULUS-framed share
Enables agents and CI jobs to verify Ed25519-signed tool-call receipt logs and check assistant replies for unsupported action claims, and to corroborate web sources by collapsing syndicated duplicates. It exposes narration verification, log verification, and source corroboration as stdio MCP tools.
Zero-key on-chain intelligence for Base, Ethereum, and Solana. Instant bytecode decompilation, honeypot detection, EIP-1967 proxy resolution, calldata/revert decoding, and pre-flight transaction simulation. No API keys or wallet connection required.
MCP server for autonomous end-to-end testing with Wopee.io. Analyzes web applications, generates and executes Playwright-based functional tests, and validates results — all driven by natural language commands.
Allows Claude Code agents to pull tasks from an EasyTopic Kanban board, automate planning, commenting, approval, implementation, and closing of topics.
Interactive feedback layer that lets users pin comments on live web apps with auto-captured context (failing requests, console, AI metadata), and coding agents fix issues via MCP, turning pins green upon verification.
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
MCP server that wraps the xAI Grok API, allowing Claude and other AI agents to delegate thinking, planning, and real-time search tasks to Grok. It provides a single tool with options for different use cases including web search, Twitter/X search, and multi-agent reasoning.
Hand a human a rich interactive UI by URL from any MCP client and get structured data back: forms, approvals, surveys, pickers, editable lists. Round-trip human-in-the-loop for agents.
Ghost Hands gives agents governed, recorded, replayable hands on the web through a zero-dependency Python CDP stack, classifying every action before it runs and writing it to a provenance trail.
Prevents coding agents from repeatedly attempting the same failed fix by tracking attempts and blocking further fixes until the agent uses its own web search tool.
Exactly-once execution for irreversible agent actions: an agent claims the right to run an effect, and a retry after a lost response returns the sealed result instead of charging again. 12 tools over stdio, including a gateway mode where the agent holds a single-use ticket and never the provider key.
Enables MCP clients like Claude to interact with any A2A agent as four callable tools, handling multi-turn memory, long-running turns, and separating reasoning from answers.
Enables external agents to deliver queue, steer, and task messages to a running dsh web instance and query session status, with configurable trust and dangerous-command filtering.
Lets a frontier coding agent delegate research, cataloguing, and long-running computation to a local LLM with guarded filesystem, web, and Python execution tools, preserving the agent's context and tokens.
Lets an AI agent ask real humans a question when the web genuinely has no answer, and get verbatim replies back with a respondent count. Built for the moment an agent is about to say "you should validate this with real users". Remote MCP, plain POST, or a single GET. No signup, no API key.
An MCP server that splits coding work between ChatGPT web (planning, review) and Codex CLI (implementation), enabling agentic workflows over a local repo with risk-gated execution and safety rails.
Paid web research MCP tools for autonomous agents: search, page extraction, citations, and diff monitoring through a live x402 API. Unpaid calls return the Base USDC payment requirement so agents can pay and retry safely.
Sovereign AI Security Suite & Threat Scanner. Real-time detection for phishing URLs, zero-day web threats, quishing QR codes, prompt injection defense, carrier disarming (AI-CDR), and autonomous agent safety guardrails.
Enables AI clients to perform autonomous multi-agent deep research through MCP tools, including deep research, quick search, and retrieval of archived Markdown reports with live web search and source citations.
Enables AI agents to automatically inspect and fill web application forms on job application sites through a logged-in Chrome, supporting text, select, radio, date, cascading dropdowns, and dynamic row operations.
Enables main agents to delegate memory retrieval, web research, and multi-step tasks to internal sub-agents, returning concise conclusions while keeping detailed tool calls and raw content out of the main context.
Enables MCP clients like Codex CLI and Claude Code to delegate tasks to a local DeepSeek Harness (dsh), with native Web transport for visible progress, model selection, and persistent long-running jobs, plus an ACP-compatible transport.
MCP server that establishes feedback-oriented development workflows with dual Web UI and desktop application interfaces, enabling AI to confirm with users via prompts and real-time feedback to reduce speculative operations and improve efficiency.
Provides access to over 100 curated AI agent skills from organizations like Anthropic, Vercel, and Hugging Face. It enables AI assistants to perform specialized tasks including document processing, security analysis, and web development through a standardized interface.
Enables Large Language Models to play chess agentically with real-time HTML board visualization and a hybrid AI engine featuring ten difficulty levels. It supports interactive games between users and agents, including a web dashboard to monitor active matches.
Enables parallel Kimi Code sessions to exchange plain-text messages through the local REST API of kimi web, with tools to list sessions, send addressed messages that can steer a running turn, and read recent messages including replies. Delivery relies on Kimi's native prompt queue, so no broker or persistent server process is required.
Enables Claude Code to delegate autonomous web browsing, deep research, and multi-tab management to a Comet browser session, with tools for asking questions, capturing screenshots, managing tabs, switching modes, and uploading files.
Enables prompt optimization loops and regression test suites for Claude Code, with a companion web UI for real-time visualization of scores and prompt revisions.
Connects Claude to Perplexity Comet's agentic browser for autonomous web browsing, deep research, and real-time task monitoring. Enables Claude to delegate web research tasks and receive comprehensive results through multiple browsing modes.
Enables a scheduled agent to assemble a Spotify discovery playlist for each genre lane, with the server handling release feeds, Spotify verification of web-researched finds, deduplication, pick-limit enforcement, carry-over pools and state persistence so the model only judges which tracks to pick. It also tracks learned labels across runs and emits per-lane reports for delivery.
MCP server that lets Claude Code delegate heavy tasks (file analysis, deep search, web lookups, adversarial review, and general delegation) to the Antigravity CLI (agy), with model routing, session continuity, timeout controls, and quota-aware failover.
Provides advanced image analysis capabilities including object recognition, OCR text extraction, and multi-turn visual dialogues using OpenAI-compatible APIs. It supports both local files and Base64 inputs with additional features for session persistence and web-based configuration management.
Enables autonomous task execution by dynamically searching APIs, generating Python tools, and running them on-demand, with built-in web search, scraping, and file operations.
Autonomous LLM-powered web crawler with 17 browser tools and goal-driven agent. Single Rust binary with stealth browsing, provider-agnostic LLM support, and built-in MCP server.
Enables agents to play a compatible real-time strategy game by observing matches and issuing typed orders for economy, construction, training, formations, naval transport, combat, and capture through five MCP tools.
A local, auditable multi-model workflow engine that lets you define YAML graphs for orchestrating LLM agents across vendors, with MCP tools for validation, dry-runs, execution, and human approval, all fully observable in a local web interface.