Coding Agents – MCP servers
93 MCP servers in the category Coding Agents. Open-source Model Context Protocol (MCP) servers that let AI assistants and agents use external tools and data. Entries come from the community list awesome-mcp-servers; we have not tested each server, so check the repository before you install one.
5dive-ai/5dive-mcp
Manage a 5dive agent fleet: file tasks, message and inspect agents, and read the fleet digest.
abnegate/magents
Shared session bus for coding agents such as Claude Code, Codex and Grok: list, read, hand off, message and spawn live agent sessions via MCP or CLI.
agent-blueprint/mcp-server
Explore and download AI agent blueprints: list them, get summaries and download full Agent Skills directories for coding agents to implement.
agentic-mcp-tools/owlex
AI council: query CLI agents (Claude Code, Codex, Gemini and OpenCode) in parallel with deliberation rounds.
alpadalar/netops-mcp
DevOps and networking tools: network monitoring, system diagnostics, automation workflows and infrastructure management.
andreilungeanu/cursor-delegate-mcp
Delegate multi-file implementation to Cursor's CLI agent over ACP and get typed results: final message, changed files, session ID and plan.
aresyn/codex-control-plane-mcp
Control plane for long-running Codex Desktop tasks: submit asynchronously, poll state, approve Plan Mode, recover retries and search SQLite-backed…
automateyournetwork/pyATS_MCP
Structured, model-driven interaction with network devices via Cisco pyATS.
AV-Labs-Co/cos-codex-bridge
Local MCP that lets a Chief of Staff client find, create and register Codex projects; submit exact prompts; track durable receipts; continue…
avansaber/tailtest-cline
Adversarial test generation in Cline: detects the stack, writes and runs tests, and classifies failures as real bugs, environment problems or test…
aybelatchane/mcp-server-terminal
Interact with TUI/CLI applications through a structured terminal state tree with element detection, like Playwright for terminals.
aymericzip/intlayer
IDE assistance for the Intlayer i18n/CMS tool: CLI access and documentation.
blakerouse/ssh-mcp
SSH control for Linux and Windows servers, with long-running commands and execution on multiple hosts at once.
bshea-1/Routed
Local router for Agent Skills across coding agents and MCP clients, with hybrid matching on the local CPU that spends no tokens.
claimidx/claimidx
Shared, signed index of failures other coding agents already solved: check it before retrying and ingest fixes so the next agent does not repeat the…
danieldoderlein/llm-bus
Coordination bus for multiple coding agents: atomic claims, advisory file leases, a shared event ledger, presence, handoffs and a task graph.…
dimitrihilverda/claude-session-relay
Self-hosted relay where coding-agent sessions on different machines share a team board, message each other and check for git conflicts, with…
djerok/glm-mcp
Run GLM (Zhipu/Z.ai) as a sub-agent in Claude Code or GitHub Copilot with its own read/write/edit/run loop, Opus-vs-GLM routing and diff/dry-run…
doggybee/mcp-server-leetcode
Search, retrieve and solve LeetCode problems, with metadata filtering and access to user profiles, submissions and contest data.
dugubuyan/agent-nexus
Document exchange for coding agents across services: versioned Markdown store, pub-sub notifications with structured diffs and lifecycle stage…
eabz/tirith
Coordinate parallel coding agents: TTL file claims, a task board with dependencies, versioned interface contracts, change notices and a decisions log.
eirikb/any-cli-mcp-server
Turn any CLI tool with --help output into an MCP server, with caching.
ejentum/ejentum-mcp
Reasoning, code, anti-deception and memory tools for AI agents.
elhamid/llm-council
Multi-LLM deliberation with anonymized peer review: parallel responses, anonymous ranking and synthesis, based on Andrej Karpathy's LLM Council…
eliottreich/taskbounty-mcp-server
Post and fund TaskBounty bounties for GitHub bugs and test coverage, or solve them with PRs that include regression tests and are verified in a…
EngMarchG/agent-bridge
Lets Claude Code and Codex steer each other's live desktop chats through Windows UI Automation: list and read chats, send messages or mid-turn…
ezyang/codemcp
Coding agent with basic read, write and command line tools.
ferrislucas/iterm-mcp
Access iTerm: run commands and ask questions about what is shown in the terminal.
foldwork-dev/mcp-injector
Local daemon that pre-indexes a codebase into a SQLite catalog and serves AST-compressed snapshots on every query to reduce token usage.
freema/openclaw-mcp
Delegate tasks to OpenClaw AI assistant agents with sync and async tools.
g0t4/mcp-server-commands
Run arbitrary commands and scripts.
gabrielmaialva33/winx-code-agent
Rust reimplementation of WCGW for coding agents: shell execution and file management.
Get-Concord-AI/concord-mcp
Communication and shared work state across coding agent harnesses: live messages, scope claims before editing, preserved decisions and evidence…
hampsterx/claude-mcp-bridge
Wraps the Claude Code CLI as MCP tools for queries, search, structured output and sessions, with budget caps and granular tool sandboxing.
hellob1889/Pandaone-AI-Agent
Requires every AI agent code change to leave a problem, reason and approach audit record before commit, with a pre-commit hook and audit trail…
irskep/persistproc
See and control long-running processes such as web servers: start, stop, restart and read logs.
jigyasudham/veto
Specialist agent council for AI coding CLIs with a self-learning router, cross-CLI memory and guards against dependency hallucinations and decision…
jinzcdev/leetcode-mcp-server
Access LeetCode problems, solutions, submissions and public data, with optional login for user features such as notes; supports the global and China…
juehang/vscode-mcp-server
Work in a VS Code workspace: read the directory structure, see linter and language server problems, read code files and make edits.
Keesan12/martin-loop
Governed runtime for AI coding agents with budget caps, verifier gates, runaway-loop prevention, rollback evidence and inspectable run receipts.
Komdosh/komnet
Git-backed message bus for coding agents on different machines, with no server: questions, answers, decisions, claimable tasks and delegated repo…
lawrencehui/Citio
Self-hosted Slack bot: mention it and Claude Code or Codex investigates CloudWatch logs, runs tests and opens PRs, with credentials held by an MCP…
louis030195/terminator-mcp-agent
Desktop GUI automation on Windows, macOS and Linux via accessibility APIs instead of screenshots, plus workflow recording, data extraction and DOM…
Luckycat133/traecnclaw-mcp-skill
Local server and Agent Skill for TraeCN desktop automation on macOS.
ly8427/mcp-review-board
Localhost review board where different coding agents (Claude Code, Codex, OpenCode, Trae, ZCode) review each other's work: objections must state…
maxim-saplin/mcp_safe_local_python_executor
Safe Python interpreter based on Hugging Face smolagents' LocalPythonExecutor.
micl2e2/code-to-tree
Convert source code into an AST, regardless of language.
misiektoja/kill-process-mcp
List and terminate OS processes via natural language queries.
MladenSU/cli-mcp-server
Command-line execution with customizable security policies.
myelixlabs/synapse-mcp
Convert a codebase into a local AST knowledge graph that gives coding agents structural context for navigation and refactoring.
nandhakumar-murugan/gemini-antigravity-bridge
Bidirectional bridge between Gemini Spark and the Antigravity IDE: coding subagent dispatch, shared memory, local file operations and Spark app…
natiixnt/redcon
Deterministic repository context packing for coding agents: selects, compresses, caches and budgets only the files a task needs, without an LLM in…
nesquikm/mcp-rubber-duck
Bridge to multiple OpenAI-compatible LLMs for rubber duck debugging: explain a problem to several AI ducks and get different perspectives.
nihalxkumar/arch-mcp
Search the Arch Wiki and AUR, get package info, check for updates, install packages and analyze PKGBUILDs, from Arch or non-Arch systems.
ooples/mcp-console-automation
Console automation and monitoring, like Playwright for terminal apps: session management, SSH, testing, monitoring and background jobs.
oraios/serena
Coding agent that uses language servers for symbolic code operations.
OthmaneBlial/term_mcp_deepseek
Approval-first local terminal control: policy-based command planning and approval, DeepSeek as an advisor, and signed execution receipts.
pdavis68/RepoMapper
Dynamic map of chat-related repository files with their function prototypes and related files, ranked by relevance, based on Aider's Repo Map.
plori-ai/plori
Create and drive hosted plori agents with persistent disk, tools and memory: invoke agents, manage the human-in-the-loop queue and schedule deferred…
polymatx/dibs
Coordinate parallel coding agents: TTL file claims across git worktrees, hooks blocking colliding edits, presence, handoff notes and searchable…
preflight-dev/preflight
Catch vague Claude Code prompts before they waste tokens: prompt scorecards, session history search, cross-service contract awareness and cost…
PsChina/deepseek-as-subagent
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.
Q00/ouroboros
Local agent OS for spec-first AI coding: a replayable, ledger-recorded interview, seed, execute, evaluate and evolve loop that MCP clients can drive.
religa/multi-mcp
Parallel multi-model code review, security analysis and debate with ChatGPT, Claude and Gemini, including consensus and OWASP Top 10 checks.
REX-codebase/fable-mode
Control plane for AI coding agents: time-locks writing, requires evidence for claims, runs adversarial review and keeps a sealed verification record.
Rikinshah787/dotpals
Checks what local coding agents such as Claude Code, Codex and Cursor really did: files changed, commands run and test results read from test…
rinadelph/Agent-MCP
Framework for building multi-agent systems that coordinate over MCP, with task management, shared context and RAG.
sena-labs/oz-mcp-server
Unofficial bridge from Warp's Oz coding agent to any IDE or MCP client, plus native @oz in VS Code Copilot Chat.
shashankss1205/codegraphcontext
Index local code into a graph database to give AI assistants context, with graphical code visualizations for humans.
sim-xia/blind-auditor
Make AI self-correct its generated output through prompt injection, independent self-auditing and context isolation.
sim-xia/skill-cortex-server
Use Claude Code Skills from any IDE or CLI.
sipyourdrink-ltd/bernstein
Deterministic orchestrator for CLI coding agents such as Claude Code, Codex and Aider, with per-agent git worktrees, an audit trail and cost-aware…
sonirico/mcp-shell
Run shell commands securely, auditably and on demand in isolated environments such as Docker.
spyrae/claude-concilium
Multi-agent consultation for Claude Code: MCP servers wrapping Codex, Gemini and Qwen CLIs for parallel code review and problem-solving with…
sshahzaiib/agy-bridge
Delegate tasks to the Antigravity CLI (Gemini): file analysis, repo archaeology, web lookups and second-opinion code reviews, with quota-aware model…
stippi/code-assistant
Coding agent with basic tools for listing, reading, editing and writing files, running commands and web search, supporting multiple projects at once.
SunflowersLwtech/mcp_creator_growth
Learning sidecar for AI coding assistants: quizzes developers on AI-generated changes and gives agents persistent project-specific debugging memory…
TheBlueHouse75/hermes-action-bridge
Delegate real-world actions to Hermes Agent: research, browser workflows, messaging, scheduling and skills, with risky actions requiring approval.
tiianhk/MaxMSP-MCP-Server
Coding agent for Max (Max/MSP/Jitter), the visual programming language for music and multimedia.
Touchpoint-Labs/touchpoint
See, find and interact with UI elements in any desktop application, like Playwright for the whole OS.
TT-Wang/forge
Structured planning and validation for Claude Code: turns an objective into a validated DAG of modules built by worker agents in parallel git…
tufantunc/ssh-mcp
SSH control for Linux and Windows servers: execute remote shell commands with password or SSH key authentication.
tumf/mcp-shell-server
Secure shell command execution.
umum-ai/claude-codex-bridge
Run Codex agents from Claude Code through MCP and Channels, with live progress notifications, mid-task steering and session continuation.
VertexStudio/developer
Developer tools for file editing, shell command execution and screen capture.
VibeKit-Bot/vibekit-mcp
Build, deploy and manage hosted VibeKit apps, each with a live URL and its own persistent server-side agent to chat with.
VoDaiLocz/kilo-kit-mcp
Runtime and skill library for coding agents: C4 workflow gates, guarded command execution and reasoning engines like Tree of Thoughts and 5 Whys.
wende/cicada
Code intelligence for Elixir: module search, function tracking and PR attribution via tree-sitter AST parsing.
wonderwhy-er/DesktopCommanderMCP
Manage and execute programs, and read, write, search and edit code and text files.
wulun811/LiuHe
Code tools for LLMs to read, understand and modify code, using a tree-sitter parser, SQLite index and transactional writes.
x51xxx/codex-mcp-tool
Connect an IDE or AI assistant to Codex CLI for code analysis and editing, with support for multiple models.
x51xxx/copilot-mcp-server
Connect an IDE or AI assistant to GitHub Copilot CLI for code analysis, review and batch processing.
Yomiracle/trinity-lite
Local task bus for CLI AI agents such as Codex and Claude Code: route work, persist state in SQLite and collaborate through a shared server.