"Agent File Control MCP Server" matching MCP servers:

Start, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, watch its events, reply, approve the tools it wants to run, and stop it. Runs over stdio, HTTP, or AWS Lambda with pluggable auth.

Enables centrally authoring and validating reusable agent guidance and delivering it across MCP-compatible hosts via registry resources, prompt templates, skill execution, and shared state.

MCP server for agent interaction with user-approved Google Chrome tabs, enabling tab listing/control, navigation, clicking, filling, snapshots, and screenshots via a local authenticated bridge.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Enables AI assistants to control a real web browser through 42 MCP tools for navigation, clicking, typing, forms, file handling, data extraction, CAPTCHA solving, and browser sessions. It also supports multi-agent isolation, persistent profiles, identity vaults, and agent-to-agent messaging.

Enables AI assistants to control and inspect the user's actual Chrome browser via MCP, preserving login sessions and isolating agent tasks in background tab groups without disrupting the user's workflow.

Enables LLMs to orchestrate AI agents and tasks, inspect DAG workflows, monitor cluster metrics, and perform safe database queries and statements through standardized MCP tools.

Provides reusable authenticated Chromium identities and one shared-control Session Browser per DSH session, enabling an agent to drive the browser through Playwright MCP while a user operates it via noVNC.

Enables users to deploy a production-grade control plane for agents, providing a spec-compliant MCP server, scoped tool grants, failure-mode detection, and cost governance.

Enables AI coding agents running in separate apps to exchange messages, tasks, presence, and context through shared rooms, direct threads, and webhook wake-ups. A human owner stays in control by approving proposed plans before execution and reviewing posted results, with safety limits on agent-to-agent chatter.

An agent gateway that aggregates multiple local MCP servers into a single MCP endpoint with runtime control, hot-reloadable configuration, and meta tools like bridge__execute for calling any child server tool without restart.

Enables governed MCP agent tool invocation with policy-based authorization, short-lived credentials, and audited access control.

Enables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts.

Enables ESP32 XiaoZhi voice devices to command a Windows PC via MCP, including app control, file operations, screen vision, browser interaction, shell execution, and orchestration of local AI coding agents like Codex CLI and Claude Code.

Hosted MCP endpoint (paid) for OpenAI Codex agent coordination, providing structured JSON tools for mail threads, updates, file leasing, and room status receipts.

MCP server that wraps agent-browser to let LLMs control a real browser, providing tools for navigation, interaction, reading page content, accessibility snapshots, screenshots, and session management.

Enables multi-agent communication between AI agents via MCP tools with real-time message routing, admin control, and dual-language support.

An MCP (Multi-Agent Conversation Protocol) Server that enables interaction with AWS S3 Control API through natural language, auto-generated using AG2's MCP builder.

MCP wrapper for the agent-msg.sh file-based message bus, enabling MCP-compatible clients to send, receive, and manage inter-agent messages with bound identity and HMAC-signed payloads.

A full-stack Agent project built from the JSON-RPC protocol layer to the LLM orchestration layer, featuring a custom ReAct loop engine, dual Provider abstraction, and permission control for Agent scenarios.

Durable MCP control plane for coordinating agent networks, with message ledger, idempotent delivery, and cryptographic identity for each orchestrator.

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 LLMs to communicate with Agent-to-Agent (A2A) protocol compliant agents, providing tools for sending messages, managing tasks, and retrieving agent information.

Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This package wraps the same engine that powers agent-ready.dev as an MCP server, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.

Enables separate desktop IDE agent hosts to hand off and review code tasks through a shared, contract-driven MCP bus with deterministic state transitions, file SHA-256 verification, and schema-validated outputs.

Enables Claude Code, Codex CLI and Antigravity (Gemini) agents to exchange messages that are pushed live into each other's open sessions, with mail_send, mail_check and mail_peers tools so no agent has to poll. Mail can also be bridged over SSH between machines with no shared filesystem.

An advanced MCP server that implements sophisticated sequential thinking using a coordinated team of specialized AI agents (Planner, Researcher, Analyzer, Critic, Synthesizer) to deeply analyze problems and provide high-quality, structured reasoning.

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.

pay-per-call x402 API endpoints as MCP tools — web search, page-to-markdown, PDF extract, JSON repair/validate, crypto price, weather, IP geo, DNS, markdown lint + 20 agent-commerce aliases. Each tool proxies to vibes-coded.com and settles via x402 (USDC/Solana). Free-trial endpoints need no auth; paid ones need an x402 signature. Catalog is fetched live, so new endpoints appear automatically.

Discovery and live reliability registry for AI agents: search 700+ verified APIs, MCP servers and CLIs, check real-time health before calling, and find working alternatives.