MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,967 servers in this category.
Coordinates specialized AI sub-agents to architect, code, and audit software engineering tasks locally using Google Gemini.
A terminal and CI harness for testing Model Context Protocol servers using a small assertion language and golden-file snapshots.
Enables AI agents to discover and track currently available free LLM APIs and their capabilities through live radar and fallback chains.
Provides local web search via SearXNG and persistent memory management for coding agents using disk-based storage and hybrid semantic search.
Analyzes Python web projects to find reachable security vulnerabilities in FastAPI and Flask routes and provides path-to-bug explanations.
A local MCP server that orchestrates multi-agent coding workflows by routing roles to isolated accounts and verifying changes through automated tests.
Provides a production-ready foundation for building MCP servers with bearer authentication, rate limiting, and structured logging.
An analytics agent that converts plain English questions into governed SQL queries using a semantic layer and multi-layer guardrails.
A chaos engineering proxy that injects timeouts, errors, and schema drift into MCP integrations to test AI agent resilience.
Enables AI agents to read, search, filter, and perform root-cause diagnosis on local log files using a rule engine or local Ollama models.
Enables AI agents to perform secure, sandboxed static reverse engineering on untrusted binaries using a no-network bubblewrap chamber.
Provides an MCP benchmark environment for testing an AI agent's ability to perform a complex mechanical repair task through tool calls.
Provides AI coding agents with cross-repository code access, agreed API contracts, and change-request history to prevent guessing across systems.
Allows an AI agent to inspect, author, and import resources into GameMaker projects using the gm-cli command-line tool.
Enables AI agents to perform malware reverse-engineering through static triage, x64dbg debugging, Frida instrumentation, and PE unpacking in an isolated lab.
Enables AI clients to develop, review, and verify FastAPI applications through specialized skills, agents, and MCP tools.
Provides assurance-as-code to test prompts, verify agent trajectories, and generate portable evidence for AI workflows.
Orchestrates AI coding agents to execute Markdown task lists, run tests, review diffs, and commit finished work automatically.
An agent that investigates GitHub repositories, issues, and source code to provide conclusions with cited sources.
Independently verifies AI agent work in local git repositories by running targeted checks and cross-referencing agent claims with actual code changes.
