"Interacting with a webpage using a browser plugin and live browser instance" matching MCP servers:

Enables AI tools to interact with browsers for enhanced frontend development, providing context to LLMs through tools like API call analysis, screenshots, element selection, and documentation ingestion.

Enables a local Codex chat to ask a second opinion, review staged, unstaged, or revision-based diffs, and delegate coding tasks to the Antigravity CLI running in isolated or disposable workspaces. Supports starting, polling, retrieving, and cancelling tasks with returned answers, diffs, changed-file lists, exit codes, and time/output limits, while never auto-applying returned patches.

A local MCP bridge that lets ChatGPT chat mode operate the user's own computer, running project, file, and shell tasks through a local executor and returning progress and results to the conversation. It also coordinates Codex sessions (persistent or one-off) and other agent CLIs as sub-agents.

Enables ChatGPT web to read local files, search code, run shell commands, and drive a local Codex CLI via an official MCP connector, with human approval for risky commands and full audit logging.

An authenticated OpenAI-compatible inference gateway with an async job broker that bridges a coding agent to a ChatGPT MCP worker, enabling ChatGPT to process inference requests via a tunnel.

Enables deterministic multi-agent pipelines in VS Code and GitHub Copilot, with 25 specialized AI agents and a 9-stage state machine that prevents hallucinated routing.

Enables coding agents to access project data with tenant-scoped permissions, using the user's own credentials instead of a service account.

Enables AI coding agents to read and write a user's Figma file through the Figma Plugin API, offline and privately, without API tokens or rate limits.

Enables Codex to delegate tasks to Claude Code, allowing Claude to investigate, edit, and verify changes in the repository with background job management.

Enables Grok Build to orchestrate the local Codex CLI for code reviews, adversarial reviews, task rescue, session transfer, and background job management through MCP tools.

Enables Claude Code sessions to wait for a durable, exact-head GitHub pull-request review and continue the same review/fix/push loop without polling, using Supabase durable state and Realtime wake-ups via ordinary stdio MCP.

Delegates coding tasks to the local Claude Code CLI via MCP, offering run, review, and status tools for MCP-compatible agents.

dev-brain-mcp

Enables AI coding agents to retrieve relevant execution context before a task, compare candidate paths, log outcomes, and search past experiences stored locally in SQLite. It lets agents reuse what worked on similar tasks and get live alerts when a run stagnates or repeats failures.

A generic OpenAI-compatible subagent MCP server that lets Claude Code delegate coding grunt-work to a local model via a tool-calling agent loop, with configurable concurrency and backend.

Enables coding agents to write repository documents (READMEs, RFCs, design docs, ADRs) from verified codebase facts, using a separate model for drafting and agent fact-checking for accuracy.

MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.

A stdio MCP server that lets Claude Code delegate coding tasks to an OpenCode instance (optionally attached to an internal LLM gateway), with follow-up replies, status polling, output/diff retrieval, cancellation, and cleanup handled in a single session. It supports managed or attach modes, sandbox and approval policies, parallel fan-out delegations, and read-only review workflows.

Provides coding agents live access to shadcn-style component registries, enabling them to search, compare, and fetch real component source code for UI composition.

Lets Claude Code delegate bounded coding tasks to a GLM model as a sub-agent through a single MCP tool that reads, writes, edits, lists directories, and runs shell commands inside a specified project folder. Each run returns only a short report with changed files and token usage, keeping GLM's intermediate tool traffic out of Claude's context.