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.
Enables AI clients to discover and retrieve read-only Procore project data, including RFIs, submittals, and documents, through a safety-first Python SDK.
Provides a collection of functional Python-based MCP servers demonstrating tools, resources, prompts, sampling, and HTTP transport with authentication.
Evaluates AI agent competence in routing Swahili institutional requests across East African coordination services.
An OpenAI-compatible gateway that fuses any LLM with a reusable fabric of MCP servers to create tool-augmented virtual assistants.
Redacts secrets and PII from MCP traffic using a reversible local proxy to prevent data leaks to third-party servers.
Provides Claude Code with local GraphRAG memory for documents and codebases using LightRAG and Ollama without cloud dependencies.
Enables AI-assisted UI and API automation testing using Playwright, Python, and MCP concepts to accelerate the software testing lifecycle.
Enables AI clients to perform hybrid RAG search over engineering documentation including PDFs, spreadsheets, and technical drawings.
Performs dynamic red-team probing of MCP servers to identify security vulnerabilities mapped to the OWASP MCP Top 10.
Provides a security gateway for MCP servers to defend against prompt injection and enforce least-privilege tool access through policy-as-code.
A statistical regression harness that measures the impact of tool description changes on agent task success and provides a deterministic defect linter.
Provides a unified registry and gateway to connect LLMs to East African digital infrastructure including FinTech, health, and legal data.
Verifies API capabilities, software versions, and documentation claims through callable tools to prevent AI agents from making false assumptions.
Lets AI assistants operate QGIS through a local, token-protected command interface with validated JSON commands and cartographic rule auditing.
Provides reference architectures and implementation labs for building stateful, multi-agent systems using LangGraph, Google ADK, and Python.
Provides a governance and intelligence layer for AI coding agents through model routing, security scanning, and role-aware skill packs.
Provides a sandboxed environment for AI assistants to perform secure file operations, AST analysis, and command execution within a designated codebase.
A reusable framework for building Model Context Protocol servers with an in-memory test harness and production-ready examples.
Provides persistent semantic memory, task management, and an AI agent team for coding assistants using a local DuckDB vector database.
Manages, indexes, and proxies requests across large ecosystems of MCP servers using hybrid search and an LRU-cached proxy system.
