A Nix-based configuration framework for Model Control Protocol (MCP) servers with ready-to-use packages.

Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

Cloud-native orchestrator enabling durable AI agents with tool calls, delegation, and human-in-the-loop workflows on Kubernetes.

JFrog-specific MCP enabling repository lifecycles, build tracing, runtime visibility, and integrated security data via Xray and curation.

Prompt-driven, language-agnostic code-quality analysis across 10 dimensions with git-aware comparisons.

A unified proxy aggregating multiple data sources, centralizing tool discovery, RAG-based document exchange, persistent memory, and an integrated testing playground.

MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured JSON configurations. Supports OAuth2.1, DCR...

MCP Checklists

A server that provides a set of tools for managing Nomad clusters through the MCP.

A dynamic MCP server management service that creates, runs, and manages Model Context Protocol servers on-the-fly.

This repository provides a working, deployable, open source-based, serverless MCP server blueprint with an AWS Lambda function and AWS CDK Python code with all the best practices and a complete CI/CD pipeline.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Robust Bitrise API access enabling app management, builds, and artifacts with secure token authentication and comprehensive, well-organized documentation.

An SSE-based interface enabling LLM-powered apps to query OCI registries for image facts like metadata, tags, manifests, and configs with secure, token-based authentication.

Panther-based interface enabling natural-language detections, interactive log queries, and AI-assisted alert triage across Panther SIEM for security teams.

Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI models to MCP servers via stdio and SSE

The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Jenkins tools while maintaining data privacy and security.

Local Glean integration enabling fast experiments with Docker or npx, with configurable clients and remote update support.

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

Run and monitor MCP servers locally

Real-time vulnerability scanning for npm dependencies with remote registry checks and remediation guidance.

Real-time system metrics exposed through a compatible interface for LLMs, covering CPU, memory, disk, network, host, and process data.

Connects AI agents to Jira and Confluence enabling data queries and actions via a standardized interface.

Unified proxy aggregating resources, tools, and prompts from multiple backends with centralized routing and consistent URI schemas across all connected endpoints.