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.
Lets AI coding agents search local OpenCode conversation history to avoid repeating past work or re-diagnosing solved bugs.
Lets AI agents control a real Firefox browser via Selenium WebDriver to navigate, interact with elements, and diagnose web issues.
Enables image-capable AI models to analyze video by extracting timecoded frames and retrieving detailed metadata like scene cuts and loudness.
$claude mcp add mcp-video-frames -- uvx mcp-video-frames
Indexes codebases to enable semantic and keyword-based search for AI agents using tree-sitter and ONNX-based embeddings.
Turns serial ports into a persistent, reviewable service with ring buffers and MCP tools for AI agents to interact with hardware.
Provides an AI client with full shell access, SSH fleet management, interactive PTY sessions, and SFTP file transfers with built-in auditing.
Allows AI assistants to execute bash commands, transfer files via SFTP, and manage Proxmox LXC containers through SSH.
Enables LLM agents to profile tabular files like CSV, Parquet, and Excel to extract schemas, statistics, and data quality insights.
$claude mcp add data-profiler-mcp -- uvx data-profiler-mcp
Provides persistent memory via SQLite and Postgres alongside a sandboxed task queue for agentic workflows.
Statically scans MCP tool manifests and runs prompt-injection attack suites to detect security vulnerabilities like tool poisoning and jailbreaks.
$claude mcp add sentinel-scan-cli -- npx -y sentinel-scan-cli
Provides an AI coding assistant with offline access to local Qt 4.8, Qt 5, and Qt 6 documentation via full-text search and Markdown extraction.
$claude mcp add qt4-doc-mcp-server -- uvx qt4-doc-mcp-server
Connects MCP clients like Claude Code to local LLMs via LM Studio, enabling autonomous tool use and multi-model orchestration.
Creates SSH tunnels to remote hosts and provides an interface for agentic AI to manage remote files, hosts, and system operations.
Provides AI assistants with PyPI package metadata and vulnerability auditing against the OSV database.
Provides persistent memory for coding agents by saving and recalling preferences, decisions, and fixes across sessions.
$claude mcp add bantamkit -- npx -y bantamkit-mcp
Search, install, and manage AI agent skills, loops, and bundles using a local CLI or a self-hostable registry.
$claude mcp add --transport http loopskill-api https://app.loopskill.io/api/mcp/http/
Lets AI assistants read, create, and manage issues, repositories, pull requests, and releases on Gitea, Forgejo, or Codeberg instances.
$claude mcp add gitea-mcp -- uvx gitea-mcp
Analyzes Lean 4 and Metamath formal libraries to identify dependencies on axioms, compiler trust, or unfinished proofs.
$claude mcp add gonzalgo -- uvx gonzalgo
Provides AI agents with read-only CVE intelligence, remediation playbooks, and evidence-gated vulnerability remediation workflows.
$claude mcp add --transport http security-recipes-ai https://security-recipes.ai/mcp
Lets an AI client configure, diagnose, and troubleshoot iNAV flight controllers over USB for fixed-wing aircraft.
$claude mcp add inav-mcp -- uvx inav-mcp