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.
A local-first governed memory engine that provides cross-session retrieval, error follow-up, and knowledge compaction for AI coding agents.
Lets AI agents read, update, and manage company documentation and engineering guidelines through a centralized GitHub-based repository.
Consolidates AI agent playbooks into a single source of truth and provides deterministic, low-latency skill routing via MCP.
Indexes Markdown and text files using BM25 and local Ollama embeddings to provide semantic and keyword search for coding agents.
Provides a governed Windows runtime for AI agents with scoped filesystem access, durable command execution, and resource management.
Reduces LLM context costs by using a small calibrated model to rank files, select tests, sort failures, and review code diffs for coding agents.
Provides a semantic vector search engine and catalog for AI agent skills, MCP servers, project directives, and system rules.
Provides an agentic framework for AI software assurance, architectural blueprinting, and active guardrails during AI-driven development.
Generates Python code for Meritz Securities Open API calls, including REST and real-time WebSocket implementations, without requiring an app key.
A Lua engine that simulates the Fibaro HC3 environment for offline development and testing of QuickApps.
Identifies integration bugs between frontend, backend, and databases by analyzing source code across multiple frameworks and data stores.
A typed Python framework for implementing the Model Context Protocol tool-serving surface using Pydantic models.
Enables AI agents to index RimWorld game files, generate typed XML mod plans, validate mod structures, and diagnose game logs for mod development.
Indexes and searches cross-agent AI conversation histories using a single SQLite database and MCP server.
Converts Markdown and AI-generated drafts into professional DOCX documents using presets, templates, and structural diffing.
Performs regression testing for MCP tool responses and the observable state changes they cause in files, databases, or custom probes.
Enables AI agents to perform hybrid search and recall across local codebases, documentation, and session notes using a single SQLite file.
Analyzes public web pages to verify machine-readable metadata and structured data readiness for answer engines.
Provides an interface for interacting with Senscritique services using a Python-based MCP implementation.
Provides a zero-dependency local memory layer for AI coding agents using SQLite FTS5 for persistent, offline context retrieval.
