MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,953 servers in this category.
Performs formula-level diffs and structural audits of Excel workbooks to identify broken references, circular dependencies, and model-breaking edits.
Provides a shared playtest desk, backlog, and handoff interface for developers to coordinate tasks and bug reports with coding agents.
Automates the maintenance of AI skill libraries through backups, corruption scanning, decision logging, and health checks.
Allows AI assistants to manage local VirtualBox virtual machines, control snapshots, and execute commands directly inside guest operating systems.
Enforces, validates, and generates Conventional Commits and branch names for Git repositories.
Secures AI coding agents by intercepting and validating MCP tool calls against deterministic rules to prevent malicious injections and unauthorized actions.
A local data workbench that lets an AI client ingest, clean, profile, chart, and model datasets using reversible steps and natural language queries.
Performs automated security probing and vulnerability scanning across 9 attack classes for OpenAI-compatible LLM endpoints.
Provides a searchable catalog of over 12,000 safety-scanned AI agent skills for Claude Code, Cursor, and other MCP-compatible clients.
Enables MCP clients to use Codex as a collaborating agent by starting and continuing threads through the official Codex SDK.
Provides a governance ledger and coordination board to track approvals and prevent collisions in mixed human and AI agent teams.
Validates that MCP server tool responses are genuine by checking for disguised refusals, empty content, and output schema violations.
Lets an AI client monitor Windows system resources, analyze performance spikes, and safely terminate processes with user approval.
Manages software test reports and releases by classifying failures, detecting flaky tests, and providing AI-driven release recommendations.
Provides secure, read-only SQLite access and restricted filesystem tools for MCP clients via stdio.
Compiles SQL queries into ffmpeg commands to perform declarative video processing and metadata extraction.
Provides a curated, automated index of AI agents, MCP servers, agent skills, and multi-agent frameworks.
Allows an AI client to browse chat history, manage workspaces, edit configuration files, and update custom prompts within an ATLAS instance.
A multi-agent Python framework that transforms feature requests into fully planned, coded, and tested software projects using specialized LLM agents.
Lets coding agents record program executions and query the resulting traces for call trees, exceptions, and variable origins.
