MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,961 servers in this category.
Finds relevant MCP tools using semantic search to reduce token usage and improve discovery through natural language intent.
Provides a typed Python wrapper for Riot Games APIs and an optional MCP server to analyze League of Legends match data and player statistics.
Performs modular data quality assurance, cleaning, and preprocessing through automated pipelines and self-healing audit tools.
Generates, runs, and tests Node.js/TypeScript MCP servers directly from OpenAPI specifications using a standalone CLI.
Enables local AI agents to perform remote Linux host operations including file management and shell command execution via MCP Streamable HTTP.
Enables AI clients to discover and execute reviewed Cloudflare REST operations using request-scoped credentials.
A Python template for building MCP servers with FastAPI, Azure Entra ID OAuth proxy integration, and Docker support.
Exposes Backstage internal developer portal data to AI agents to query service catalogs, fetch documentation, and scaffold new services.
Allows an AI client to access read-only Google Analytics 4 reporting data including traffic overview, top pages, and conversion summaries.
Provides a shared, persistent vector memory for AI coding agents using Qdrant to maintain context across different tools and sessions.
Guides an AI client through building, evaluating, securing, and shipping LLM agent systems with templates, provider adapters, and blueprints.
Loads Claude-style skills from a directory and exposes each one's instructions, resources, and helper scripts as callable tools for any MCP client.
Lets an AI client run Python code and shell commands in a stateful IPython kernel and call MCP tools programmatically.
$claude mcp add ipybox -- uvx ipybox
Teach AI coding agents to audit Kafka topics, diagnose consumer lag, review schemas, connectors and DLQs, and scaffold production-ready clients.
Lets you run one connector that hosts multiple isolated MCP servers for PostgreSQL and MSSQL databases with token-based access.
Provides a repo-local continuity runtime that allows AI coding agents to resume work from a shared, inspectable state across different sessions.
A minimal AI agent built with Python and the OpenAI SDK that executes tasks through a deterministic loop using local or remote LLMs.
Lets AI coding agents recall past decisions, commitments, meetings, and daily briefings from a local personal knowledge graph.
Provides a shared, in-repo memory layer for AI coding agents to store project decisions and enforce them by blocking regressive edits and commits.
Enables an AI agent to perform autonomous evolutionary search by acting as a variation operator for code optimization and policy evolution.