MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,966 servers in this category.
An MCP server that enables teachers to write programming exams with compiler-checked solutions and printable PDF output.
Mitigates regression loops in coding agents by recording failure witnesses and gating candidate code patches through a three-state regression gate.
Provides a single OpenAI-compatible API gateway to access multiple LLMs including DeepSeek, Qwen, Claude, and GPT with ruble-based payments.
Verifies LLM citations for fabrication, retraction, or distortion and checks numerical claims against source documents.
Enables AI clients to perform local video forensics, including metadata extraction, subtitle-first transcription, frame sampling, and sound event analysis.
Provides an evidence-bound reverse-engineering harness that verifies AI agent claims against static analysis and sandboxed execution.
Decrypts and exports local WeChat PC chat data, allowing AI clients to search, analyze, and retrieve messages, contacts, and media.
Allows an AI agent to request secrets or text edits through a secure window on your screen without the agent ever seeing the sensitive data.
Exposes a typed, provenance-aware knowledge graph over an Obsidian vault to coding agents via MCP.
Allows AI agents to inspect PostgreSQL query plans and verify performance improvements through measured, rolled-back transactions.
Enables coding agents to profile, rewrite, and verify GPU kernels using Nsight, SASS, and Triton through an autonomous speedrun loop.
Enables LLMs to perform full-duplex TCP communication, network probing, and mock server simulation for IoT and industrial hardware testing.
Measures hardware energy consumption, calculates ISO/IEC 21031 SCI scores, and generates AI-powered refactor proposals to reduce software carbon footprints.
Lets an AI client perform experimental load-path analysis on 3D-printed STL parts and manage iterative CAD design sessions.
Lets an AI client diagnose Python backend stacks by analyzing Postgres, Celery, Redis, and logs in a single tool call.
Provides a deterministic physical Ising solver and hardware-accelerated equilibrium co-processor for high-frequency trading and LLM inference workloads.
Forwards JSON-RPC messages from stdio MCP clients to Ramen workers over gRPC using group keys or OAuth 2.1.
Provides an agent engineering tool directory and event information for London and San Francisco via CLI, MCP, and A2A interfaces.
Audits the security posture of remote MCP servers by checking OAuth configurations, transport hardening, and tool surface vulnerabilities.
Allows AI agents to bypass GitHub's 14-day limit by backing up, analyzing, and querying historical repository traffic metrics via a local SQLite database.
