Best Developer tools MCP servers

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

SSH server management for agents, with per-server read-only and allowlist security modes

A Model Context Protocol (MCP) server for Kubernetes and OpenShift

Tells an agent what changed on a server since it last looked - status, Docker, backups, Proxmox.

Session memory for coding agents: local-first recall, drift detection, on-device inference.

Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call

MCP server for WHOOP health data — recovery, sleep, workouts, cycles, and trends.

CesiumJS API docs, code generation and development tools for IDE AI assistants.

Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium.

Search the Claude Code Ultimate Guide and machine-readable references from any MCP client.

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

Route coding work across Claude Code, Codex, Cursor, and OpenCode with shared context.

Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.

Live layered dependency map for bottom-up development, drawn by the agent in a terminal pane.

AI-powered OSINT agent & MCP server. 21 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

Apple Human Interface Guidelines search, lookup, and project audits for AI coding agents.

Up-to-date code docs for any prompt

GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more.

Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman

One workspace for every AI coding assistant. Shared tasks, memory, and governance.

Keep the state. Change the model. Shared context and a multi-model panel across coding assistants.

A DynamoDB emulator with an MCP server exposing 35 DynamoDB tools to coding agents.

Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.

Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search

Cross-harness communication and shared work-state for AI coding agents.

One system around coding agents to run, verify, recover, and hand off software work.

Local, deterministic review of Git changes: weakened tests and CI gates, risky flows, blast radius.

Live AWS, database & Kafka infrastructure context for AI coding assistants via MCP.

Read-only SQL queries and schema inspection for IBM Db2 for i over ODBC, JT400 or Mapepire (SSH).

Local-first AI PKM memory for coding conversations.

Execution engine for AI agents. 412 modules: browser, file, Docker, data, crypto.

MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.

Claude Code drives Codex CLI's interactive TUI and durable tmux terminals over MCP.

Persistent terminals and one launcher for Claude, Codex, Grok, and Cursor harnesses.

Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.

Buddhist canon tools: search, passages, cross-canon parallels, dictionaries — all URN-cited.

Local-first project memory with legacy MCP and 2026 discovery compatibility.

TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support

Swift reviews, local Apple references, app scaffolding and iOS simulator workflows.

Temporal engineering context for agents via MCP.

Vinv runs, tests, and finds issues in your services — with zero code changes.

Autonomous spec-to-product coding-agent CLI with an MCP server exposing 39 tools over stdio.

AI code research platform. Search, analyze, and extract insights from any GitHub repository.

Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline.

Repo-native task continuity for AI coding agents: a reviewed task-state ledger served over MCP.

Server security audit (413 checks), hardening, and fleet management across 4 cloud providers.

112 rules that catch dangerous PostgreSQL migrations, plus a pass/fail gate to call before any DDL.

Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.

Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety

Mine the architecture rules your TypeScript repo already enforces, with the evidence attached.

Deterministic local-first context and impact maps for coding agents from tasks, issues, and diffs.

Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.

Graph-powered code intelligence with semantic search and knowledge graph for AI assistants

Graph context, semantic search, guarded edits, and reviewable Git for local Obsidian vaults.

Build HOI4 mods: focus trees, events, decisions, worlds, GUI previews, docs and AI balance.

Bounded local runtime evidence from explicit artifacts and typed direct targets.

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

Read, replay and fork recorded coding-agent runs.

Real production websites for coding agents: palettes, fonts, fold autopsies and reference JSX.

MCP server for PostgreSQL: local, Docker, RDS, Neon, Supabase, or behind an SSH bastion.

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.

Load-test a URL, ping it by phase, ramp to find the capacity, compare runs: JSON reports, guardrails

Token efficient search for coding agents over public and private documentation.

Check whether a coding agent's changes stayed inside the scope it was given.

deja-vu: local memory over the session histories of forty-one coding agents.

Search public open-source code, documentation, metadata, vulnerabilities, changelogs, and examples.

Quality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.

Query WHOIS/RDAP information for domains, IP addresses, CIDR prefixes and ASNs. Self-hostable.

Lets AI coding agents coordinate asynchronously through a private git repository. No server.

Operate local-ydb deployments through local or SSH-backed MCP tools.

Token-efficient code review knowledge graph: semantic search and call-graph resolution.

Secure MCP SSH automation server with policy controls, resources, prompts, stdio, and HTTP.

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

AI-powered VMware vCenter/ESXi VM lifecycle and deployment with 60 MCP tools.

AI-powered VMware vCenter/ESXi VM lifecycle and deployment with 31 MCP tools.

Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).

Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.

An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.

Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.

MCP server for Komodo - manage Docker containers, servers, stacks, and deployments via AI

Local stdio MCP server for cached, loop-aware JS/TS diagnostics (Oxlint, tsc, Biome, ESLint).

Local-first, cross-harness memory for AI coding agents.

Persistent institutional memory for AI coding agents. Memory that compounds.

Flux UI component and layout docs for AI coding agents. Live from fluxui.dev, Pro-tier aware.

An MCP Server to utilize Lineai's rich software dependency data in your AI programming assistant.

Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.

Inspectable, correctable project memory in git-versioned Markdown for AI agents.

The TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query tools

Operate self-hosted OpenClaw and Hermes agent fleets on Docker or Kubernetes from MCP clients.

Read-only codebase audits for coding agents: secrets, RLS, deps, review verdicts. No writes.

Pre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.

Kubernetes port forwarding for local development with automatic /etc/hosts entries.

UI design that stands out. Full-screen UI references and design materials for coding agents.

Design intelligence for coding agents: audits, design systems, and a taste profile agents consult.

Website QA for your coding agent: audit SEO, performance, security, accessibility over MCP.

Manage AWS, Hetzner, OVH and SSH servers: status, logs, CloudWatch, IP bans, safe command exec.

Local video studio for your coding agent: scenes, voice, music and captions, on your machine.

Preview environments on your self-hosted Spawner server: a copy of your app for each git branch

Local-first MCP server for task tracking and coordination of autonomous AI coding agents.

Context sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.

Bridge AI coding hosts to cursor-agent over the Agent Client Protocol.

PostgreSQL schema intelligence from a committed snapshot. No connection, no credentials.

Call graph for coding agents: callers up to HTTP routes, callees, usages for TS/JS, Go, Python, Java

Model Context Protocol server for Google's Jules AI coding agent

Local code search for AI coding agents: hybrid keyword + semantic + SQL over an index in your repo.

Troubleshoot Kubernetes agentically: natural-language cluster diagnosis via ask_kubently

Spawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows.

IMAP/SMTP MCP server for Email with composite tools. Multi-account, auto-discovery.

Markdown-first MCP server for Notion API with 8 composite tools and 39 actions.

File a task with your local no_human and check on it: task_add and task_status over stdio.

When the agent writes a bad import, the write doesn’t land. The same check fails the pull request.

Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.

Windows UI Automation MCP server for desktop inspection and element lookup. Windows only.

AI-powered development platform for Kubernetes deployments and intelligent automation

Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.

MCP server exposing JetBrains TeamCity CI/CD workflows to AI coding assistants

Structured build tool output (tsc, generic commands) as typed JSON diagnostics.