MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,951 servers in this category.
Enables AI agents to read, edit, validate, and procedurally generate Celeste .bin map files.
$https://github.com/Magedeline/loenn-mcp/releases/download/v7.2.0/loenn-mcp-7.2.0.mcpb
Probes, ranks, and recommends models across OpenAI-compatible gateways by measuring real-world latency, success rates, and tool-calling capabilities.
$claude mcp add modellens -- uvx modellens-mcp
Converts PDF, DOCX, PPTX, XLSX, and images into structured Markdown with LaTeX and tables via a self-hosted MinerU API.
$claude mcp add mineru-mcp -- docker run -i --rm ghcr.io/germaniu/mineru-mcp:0.1.0Enables AI agents to audit and set up site measurement using Google Analytics 4, Search Console, and PageSpeed Insights.
$claude mcp add ga4-seo-mcp -- uvx ga4-seo-mcp
Provides end-to-end encrypted secrets management and human-in-the-loop approval for AI agents using scoped machine tokens.
$claude mcp add aisecuritywarden-client -- uvx aisecuritywarden
Compare text LLMs across multiple backends with automated grading, performance metrics, and cost estimation.
$claude mcp add evalforge-lite -- uvx evalforge-liteEnables coding agents to perform semantic searches across local, GitHub, and Bitbucket repositories using a local embedding model.
$claude mcp add delphi-code -- uvx delphi-code
Provides structured failure knowledge to prevent AI agents from repeating known code errors and country-specific real-world mistakes.
$claude mcp add deadend-dev -- uvx deadends-dev
Scans Android and iOS applications for security vulnerabilities and generates pentest reports mapped to OWASP MASVS, CWE, and CVSS.
$claude mcp add gomobsec-mcp -- uvx gomobsec-mcp
Inspects AI-generated artifacts, declared claim evidence, and literal citation containment through deterministic local checks.
$claude mcp add daily-ai-agent-toolkit -- uvx dailyaiagents-evidence-gate
Discover and install Claude Code plugins, agents, commands, hooks, skills, and MCP servers from one marketplace hub.
Build and run MCP servers from Python tool, resource, and prompt files, with auth, telemetry, and a debugger.
Lets an AI client query dbt metrics and models, run dbt CLI commands, manage jobs, and search dbt docs.
Runs authorized penetration tests from recon to post-exploitation using 165+ connected red-team tools and persistent session intel.
Lets AI coding agents query a local SQLite code graph, inspect patterns, and run change-safety checks across a repository.
Lets an AI client run automated workflows that browse websites, call APIs, handle files, and record verifiable step-by-step execution evidence.
$claude mcp add flyto-core -- uvx flyto-core
Provides an evidence-grounded repository audit tool that gives coding agents structured source context, dependency graphs, and impact analysis.
Enables AI clients to interact with Binary Ninja for automated reverse engineering, malware analysis, and CTF challenge solving.
Lets AI clients query robotics, drone, and IoT log data in plain English using auditable DuckDB SQL queries and edge data reduction pipelines.
$claude mcp add bagel -- docker run -i --rm ghcr.io/extelligence-ai/bagel/ros2-kilted:2.4.1
Lets AI coding assistants run semantic code search, symbol graph navigation, and persistent memory queries over an indexed codebase.