"Calibre-Web" matching MCP servers:

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.

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.

Exposes web search and page fetching tools via the MCP protocol, allowing integration with AI editors like Cursor for autonomous research workflows.

Connects ChatGPT Web to a self-hosted local coding workbench, enabling file editing, shell commands, Git/GitHub operations, multi-workspace management, code review, terminal processes, checkpoints, and optional Docker sandboxing.

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.

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.

Enables human-in-the-loop checkpoints for AI agents, allowing them to pause and wait for human input via a web UI, then seamlessly resume execution.

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.

Remote MCP server (HTTP/OAuth) exposing a self-hosted Honcho instance to claude.ai custom connectors and other MCP clients.

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

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.