Coding agent that uses language servers for symbolic code operations.
Coding Agents
These servers expose coding workflows, agent coordination and development capabilities through MCP. Read the project documentation to understand which agent or editor it expects and what operations it can perform.

Manage and execute programs, and read, write, search and edit code and text files.
Local agent OS for spec-first AI coding: a replayable, ledger-recorded interview, seed, execute, evaluate and evolve loop that MCP clients can drive.
Index local code into a graph database to give AI assistants context, with graphical code visualizations for humans.
Desktop GUI automation on Windows, macOS and Linux via accessibility APIs instead of screenshots, plus workflow recording, data extraction and DOM inspection.
Coding agent with basic read, write and command line tools.
Deterministic orchestrator for CLI coding agents such as Claude Code, Codex and Aider, with per-agent git worktrees, an audit trail and cost-aware routing.
Framework for building multi-agent systems that coordinate over MCP, with task management, shared context and RAG.
IDE assistance for the Intlayer i18n/CMS tool: CLI access and documentation.
SSH control for Linux and Windows servers: execute remote shell commands with password or SSH key authentication.
Communication and shared work state across coding agent harnesses: live messages, scope claims before editing, preserved decisions and evidence handoffs.
Access iTerm: run commands and ask questions about what is shown in the terminal.
Governed runtime for AI coding agents with budget caps, verifier gates, runaway-loop prevention, rollback evidence and inspectable run receipts.
Work in a VS Code workspace: read the directory structure, see linter and language server problems, read code files and make edits.
Coding agent for Max (Max/MSP/Jitter), the visual programming language for music and multimedia.
Run arbitrary commands and scripts.
Dynamic map of chat-related repository files with their function prototypes and related files, ranked by relevance, based on Aider's Repo Map.
Secure shell command execution.
Delegate tasks to OpenClaw AI assistant agents with sync and async tools.
Coding agent with basic tools for listing, reading, editing and writing files, running commands and web search, supporting multiple projects at once.
Bridge to multiple OpenAI-compatible LLMs for rubber duck debugging: explain a problem to several AI ducks and get different perspectives.
Command-line execution with customizable security policies.
Access LeetCode problems, solutions, submissions and public data, with optional login for user features such as notes; supports the global and China sites.
AI council: query CLI agents (Claude Code, Codex, Gemini and OpenCode) in parallel with deliberation rounds.
Control plane for long-running Codex Desktop tasks: submit asynchronously, poll state, approve Plan Mode, recover retries and search SQLite-backed history.
Run shell commands securely, auditably and on demand in isolated environments such as Docker.
Structured, model-driven interaction with network devices via Cisco pyATS.
Convert source code into an AST, regardless of language.
Search the Arch Wiki and AUR, get package info, check for updates, install packages and analyze PKGBUILDs, from Arch or non-Arch systems.
Delegate tasks to the Antigravity CLI (Gemini): file analysis, repo archaeology, web lookups and second-opinion code reviews, with quota-aware model failover.
Console automation and monitoring, like Playwright for terminal apps: session management, SSH, testing, monitoring and background jobs.
Checks what local coding agents such as Claude Code, Codex and Cursor really did: files changed, commands run and test results read from test output, not the agent's word. Read-only.
Run DeepSeek as a sub-agent in Claude Code or Codex CLI, with its own agent loop for reading, editing and running commands in a sandboxed workspace.
Safe Python interpreter based on Hugging Face smolagents' LocalPythonExecutor.
See, find and interact with UI elements in any desktop application, like Playwright for the whole OS.
Search, retrieve and solve LeetCode problems, with metadata filtering and access to user profiles, submissions and contest data.
Code intelligence for Elixir: module search, function tracking and PR attribution via tree-sitter AST parsing.
Rust reimplementation of WCGW for coding agents: shell execution and file management.
Parallel multi-model code review, security analysis and debate with ChatGPT, Claude and Gemini, including consensus and OWASP Top 10 checks.
Structured planning and validation for Claude Code: turns an objective into a validated DAG of modules built by worker agents in parallel git worktrees.
Runtime and skill library for coding agents: C4 workflow gates, guarded command execution and reasoning engines like Tree of Thoughts and 5 Whys.
Local router for Agent Skills across coding agents and MCP clients, with hybrid matching on the local CPU that spends no tokens.
Turn any CLI tool with --help output into an MCP server, with caching.
Use Claude Code Skills from any IDE or CLI.
Connect an IDE or AI assistant to Codex CLI for code analysis and editing, with support for multiple models.
Control plane for AI coding agents: time-locks writing, requires evidence for claims, runs adversarial review and keeps a sealed verification record.
Interact with TUI/CLI applications through a structured terminal state tree with element detection, like Playwright for terminals.
SSH control for Linux and Windows servers, with long-running commands and execution on multiple hosts at once.