MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,958 servers in this category.
Enables AI coding assistants to search documentation, generate DOMQL components, audit code, and manage Symbols platform projects.
$claude mcp add symbols-mcp -- uvx symbols-mcp
Lets an AI client monitor live usage limits across multiple coding-agent subscriptions and offload tasks to providers with available headroom.
$claude mcp add agentpool -- uvx agentpool-cli
Compiles AI coding session transcripts into a searchable, interlinked local wiki for agents to retrieve past decisions and solutions.
$claude mcp add sessionwiki -- uvx sessionwiki
Provides AI agents with safe, read-only SQL access to multiple database engines including PostgreSQL, MySQL, Oracle, and SQL Server.
$claude mcp add universal-db-mcp -- docker run -i --rm ghcr.io/alghanim/universal-db-mcp:0.2.0
Converts Claude Code sessions into clean handoff documents and project memory briefs for other AI agents to continue work.
$claude mcp add claude-handoff -- uvx claude-handoff
Provides coding assistants with read-only access to the SaferAgenticAI framework, including 239 implementation patterns and 15 operational heuristics.
$claude mcp add saferagenticai-mcp -- uvx saferagenticai-mcp
Tracks uncertain values mentioned in prompts and blocks AI writes that embed those unverified values until they are confirmed.
$claude mcp add credence-ai -- uvx credence-guard
Provides a secure, containerized sandbox for LLMs to autonomously code, test, and debug using bash, filesystem tools, and uv-powered Python execution.
$claude mcp add agent-workspace-mcp -- docker run -i --rm ghcr.io/hrrodan/agent-workspace-mcp:1.4.139
Provides local-first, governable long-term memory for AI coding agents to store and recall project rules, preferences, and decisions.
$claude mcp add cp-memory -- uvx cp-memory-mcp
Performs plain-English security scans on AI-built applications and generates fix requests for coding agents.
$claude mcp add appledger -- uvx appledger
Converts web pages and raw HTML into clean, compact Markdown to reduce token usage for AI agents.
$claude mcp add domstrip-client -- uvx domstrip-mcp
Enables AI agents to search API endpoints and execute Python code in a secure sandbox with integrated memory.
$claude mcp add vibocode-mcp -- npx -y vibocode-mcp
Provides an AI client with a local, offline catalog of tools from GitHub awesome lists, searchable by name, language, platform, or topic.
$claude mcp add awesome-core -- uvx awesome-core
Verifies AI agent claims against primary evidence and provides real-time machine environment observations without using a language model.
$claude mcp add buddie -- uvx buddie
Enables AI clients to perform embedded debugging through serial communication, fault pattern analysis, flash verification, and hardware knowledge base access.
$claude mcp add mcu-debug-mcp -- uvx mcu-debug-mcp
Provides coding agents with calibrated probability scores to help them decide when to ask questions or take actions.
$claude mcp add ember -- uvx ember-advise
Enables AI assistants to annotate histopathology slides, detect nuclei, segment medical objects, and export training data in COCO, YOLO, or QuPath formats.
$claude mcp add label-image-mcp -- uvx label-image-mcp
Provides a Claude Code harness with subagents, slash-commands, and a multi-layer memory model to orchestrate AI-driven development workflows.
$claude mcp add junai -- uvx junai-mcp
Relays MCP tools to any OpenAI-compatible local LLM endpoint like Ollama, llama.cpp, or vLLM.
$claude mcp add qsp-mcp -- uvx qsp-mcpRelay MCP tools to any OpenAI-compatible local LLM endpoint like Ollama, llama.cpp, or vLLM.
$claude mcp add qsp-client -- uvx qsp-client