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.
Allows an AI agent to execute tests, parse JUnit XML results, trim tracebacks, and detect flaky tests through safe subprocess management.
Enables AI agents to run, debug, and analyze test suites for pytest, unittest, jest, and vitest with structured results and flaky test detection.
Allows an AI client to perform deep network diagnostics including TLS certificate analysis, DNS wire format resolution, and HTTP redirect tracing.
Allows an AI agent to test, explain, and stress-test regular expressions using real engines and sandboxed execution.
Diagnoses website health by performing TLS, DNS, HTTP, security header, port, and email DNS checks with specific remediation steps.
Scans repositories for TODO and FIXME markers to provide age, author attribution, and staleness analysis using git blame.
Analyzes project lockfiles and installed metadata to determine dependency licenses and compliance against a custom policy engine.
Lints and explains Dockerfiles and docker-compose files statically with rule IDs, severity levels, and concrete fix suggestions.
Allows an AI client to lint Dockerfiles and compose files by parsing grammar, analyzing cache order, and providing fix previews without requiring Docker.
Converts raw crash output from multiple languages into compact root-cause reports and maps them to your local source code.
Converts pasted crash output into root-cause reports by parsing tracebacks, chained exceptions, and multi-language stack frames.
Allows an AI client to audit GitHub Actions workflows for YAML pitfalls, security injections, permission issues, and cron syntax errors.
Audits Google Performance Max and Meta Advantage+ campaigns to expose hidden budget waste and channel spend breakdowns.
Provides ultra-low-latency Rust-based guardrails and context compression for AI coding agents like Claude Code and Cursor.
Lints MCP servers against agent-friendly design principles to ensure tools are easy for AI agents to use and interact with.
Indexes local code repositories by symbol to provide precise context spans for LLMs using a hybrid lexical and embedding retrieval engine.
Audits World of Warcraft addons for performance, usability, API existence, and security issues to assist AI coding agents.
Provides local-first memory and offline output verification for AI agents to prevent forgetting and hallucination.
Exposes command-line applications as structured MCP tools with automatic command discovery and argument validation.
Provides a production-ready template for building Model Context Protocol servers in Python with built-in testing, logging, and deployment configurations.