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.
Provides a unified interface for multiple LLM backends including OpenAI, Claude, Grok, and local models via a single MCP server or CLI.
Provides self-hosted, source-cited RAG capabilities for coding agents using hybrid LanceDB and SQLite retrieval.
Enables LLM agents to search 1C BSL code and configuration metadata using hybrid semantic and lexical retrieval.
Turns your local OpenAI Codex CLI into a persistent coding subagent for AI clients like Claude Code.
Automates Cyberpunk 2077 world building through procedural level design, asset cataloging, and mod packaging tools.
Allows an AI assistant to delegate coding tasks to Claude Code running within project dev containers via Unix sockets.
Verifies AI-written documents against a controlled facts file to ensure accuracy in numbers, skills, and terminology.
Audit project dependencies for known vulnerabilities and outdated versions by analyzing lockfiles via OSV.dev.
Audits project dependencies by parsing lockfiles and querying the OSV database to identify vulnerabilities and dependency paths.
Enables an AI agent to perform image processing tasks including resizing, size-targeted compression, EXIF privacy stripping, and thumbnail generation.
Enables AI agents to investigate large log files through streaming, timestamp normalization, multi-line event grouping, and error clustering.
Analyzes git history to identify risky files, code ownership, change coupling, and bus factor for codebase intelligence.
Scans git history and working trees for accidentally committed secrets while ensuring raw credentials never reach the AI agent.
Scans git repositories and history for sensitive credentials using regex and entropy while ensuring secrets are redacted before reaching the AI agent.
Enables AI agents to read, search, extract tables, and manipulate PDF pages with built-in safety constraints and scanned-page detection.
Allows an AI agent to inspect network ports and safely terminate processes using a token-based confirmation system.
Diagnoses project environment variables by analyzing shapes and types without ever exposing sensitive values to the AI model.
Enables an AI agent to debug web performance by analyzing browser HAR exports through streaming JSON parsing and timing calculations.
Enables AI agents to perform semantic diffing between JSON, YAML, and CSV files by identifying structural changes rather than simple line differences.
Analyzes Python and JavaScript/TypeScript projects to map import graphs, detect dependency cycles, and identify the impact of file changes.
