Packages

Provides an MCP server (Model Context Protocol) exposing read-only querying tools for Istio resources and related Envoy proxy configuration/status from Kubernetes clusters.

Provides a Claude Code “skill” that guides an agent to manage JIRA issues, projects, workflows, and Agile/Scrum operations via the Atlassian MCP server (mcp__atlassian). It includes workflow guidance, JQL construction patterns, custom field discovery approaches, templates, and troubleshooting best practices.

LeanMCP is a modular TypeScript toolkit for building and deploying MCP (Model Context Protocol) servers, providing an HTTP server runtime plus decorators-based tool/prompt/resource definitions. The README indicates optional modules for authentication, multi-tenancy, request logging, observability, and env/secret injection, along with a CLI for scaffolding and managing MCP projects.

Provides a Model Context Protocol (MCP) server that connects AI assistants to AWS CloudWatch Logs, enabling log browsing/searching, log insights-style querying, summarization, error pattern detection, and cross-service log correlation.

MCP server (Go binary) that integrates AI assistants with 1C:Enterprise by exposing MCP tools to inspect 1C configuration/metadata and perform limited query and code-related operations over a local 1C HTTP service (and an installed 1C extension).

Provides an MCP server that exposes Discord bot capabilities (server/channel/member lookup, message read/send, reactions, and basic moderation/role management) to MCP clients such as Claude Desktop.

Provides a local, read-only MCP server that wraps CData’s Office 365 JDBC driver. The MCP server exposes Office 365 entities as tools (get_tables/get_columns/run_query) so an MCP-capable client (e.g., Claude Desktop) can query live Office 365 data without manually writing SQL.

Provides an MCP (Model Context Protocol) server that helps AI clients search and explore OpenAPI specifications (from oapis.org), including generating simple-language summaries and locating relevant operations/endpoints. Supports OpenAPI files in both JSON and YAML and is intended for Claude Desktop/Cursor via an MCP URL.

Provides a Java (Spring Boot) Model Context Protocol (MCP) server that exposes UK Open Banking functionality (AISP account/balance/transactions and PISP payment initiation) to Claude Desktop via an MCP JSON-RPC (tools/list, tools/call) interface over stdio/bridge, with the server calling underlying UK Open Banking APIs using OAuth credentials.

An MCP server that exposes Oracle Cloud Infrastructure (OCI) Network Load Balancer (NLB) service APIs, enabling AI agents to create and manage Layer 4 load balancers, backend sets, listeners, health checks, and routing policies for TCP/UDP traffic within OCI.

Provides a persistent Python REPL for coding agents using a tmux-backed session so variables persist across turns. Agents write Python code to a temp file; only print() output is intended to be emitted back to the conversation context, while intermediate data stays in the REPL session.

Provides an MCP server that exposes tools for querying global supply chain and trade data, sourced from UN Comtrade and World Bank trade statistics (and an additional “Open Supply Hub” supplier database). Tools include trade flow queries, top trade partner rankings, country trade statistics, and supply-chain risk analysis, plus supplier search by country/sector.

Provides an MCP server integration that lets AI assistants control Unreal Engine (UE5.6+) through natural-language tool calls, translating them into Unreal Editor operations via an Unreal plugin and an embedded Python interpreter (spawn/edit actors, assets, materials, Blueprint graphs, behavior trees, and some editor/game settings).

Provides a local read-only MCP server that exposes Zoho CRM data through CData JDBC Drivers, wrapping the driver into MCP tools (get tables, get columns, run SELECT queries) usable by local MCP clients via stdio.

Command-line security scanner that inventories and scans locally installed agent components (MCP server configurations, MCP tool descriptions, and optionally agent skills) for common agent-supply-chain threats such as prompt injection, tool poisoning/shadowing, toxic flows, malware payloads, untrusted content, and credential/secret handling issues.

A training/repository (Python) showing how to build semantic long-term memory for AI assistants using Model Context Protocol (MCP) with FastAPI/FastMCP and a hybrid RAG architecture (vector + graph + scratchpad), including example labs (e.g., a hello MCP lab) and a flagship teaching app (WARNERCO Schematica).

HelixDB-backed MCP server for storing, querying, and updating business and customer “memory” data, including keyword (BM25) and semantic search plus relationship/interaction tracking (product/service/customer and navigation/directions).

Kafka MCP Server is a Model Context Protocol (MCP) server that lets an LLM client interact with an Apache Kafka cluster using natural-language tool calls. It provides MCP tools to inspect Kafka (e.g., topics, consumer groups/lags, broker/controller info, offsets) and to operate on topics (e.g., produce messages, create topics, consume messages). It can be run locally via Docker or as a Go binary, and supports an optional “MultiplexTool” mode to batch multiple tool calls in a single request (with optional Gemini-backed PROMPT_ARGUMENT inference).

Provides a local, read-only MCP server that exposes LinkedIn Ads data through a JDBC driver (CData) using MCP tools such as listing tables/columns and running SELECT queries. Designed to be used with local MCP-capable clients (e.g., Claude Desktop) via stdio.

mcp-server-factory is a Java (Spring Framework, not Spring Boot) MCP (Model Context Protocol) server intended as a learning tool and reference implementation. It exposes MCP tools/resources/prompts that help explain MCP concepts and generate task-planning checklists for common development activities (e.g., code cleanup, feature implementation, local MCP deployment).