Packages

A Python walkthrough/project that demonstrates how to build and run an MCP server (via the mcp[cli] tooling) to serve an ML model (described as a trained Random Forest) and integrate that capability into an agent workflow (Bee Framework for ReAct interactivity).

Indexes Claude Code session JSONL files from ~/.claude/projects/ into a local SQLite database (with FTS5) to enable fast full-text search, retrieval of conversation excerpts, analytics over usage, and cross-session synthesis (optionally using the Anthropic SDK for standalone synthesize). It can also capture live “topics” during sessions via Claude Code hooks and runs background indexing to keep the index up to date.

CLI tool that scaffolds a new Model Context Protocol (MCP) Python server project from a template, using uvx/uv for project creation and dependency management.

An MCP server that provides Google Maps-related capabilities to AI agents via the Model Context Protocol. The package name suggests it wraps Google Maps Web Services functionality (e.g., places/geocoding/routing/search) into MCP tools, allowing agents to call those tools as part of their reasoning workflows.

mcp-wechat-server is an MCP (Model Context Protocol) server that enables AI agents to perform a WeChat bot flow:扫码登录、查询登录状态、长轮询获取新消息、发送文本消息，并通过打字状态工具向对方显示“正在输入...”。它还在本地持久化登录凭证与消息游标以便重启后继续运行。

A Claude Code skill that generates Mermaid (.mmd) diagrams from user requests, validates Mermaid syntax before export, and exports to PNG/SVG/PDF using either local mermaid-cli (mmdc) or a fallback Kroki API endpoint.

mobile-mcp is an MCP server intended to let LLMs control Android mobile devices via structured UI dumps, using Node.js/TypeScript tooling and ADB for connectivity.

Prometheus MCP server that exposes Prometheus data/queries as Model Context Protocol (MCP) tools. It supports running in an SSE transport mode (per README) and optionally authenticates requests to the upstream Prometheus using environment-configured Basic Auth or Bearer token.

Redis is an in-memory data store and key-value database that also supports data structures (e.g., strings, hashes, lists, sets, sorted sets), persistence options, pub/sub, and common caching/queue patterns. It can be used standalone or as part of larger architectures.

Provides a local, read-only MCP server that exposes Splunk data (via the CData JDBC Driver for Splunk) as MCP tools. Supports listing tables/columns and running SQL SELECT queries through a JSON-RPC interface over stdio.

application-skills provides a large catalog of app-specific “skills” (one per integration) for AI agents to perform actions (e.g., Gmail/Slack/HubSpot/Salesforce) using the Membrane platform and the Agent Skills specification. Skills describe each app’s structure, available actions, and how to invoke them via compatible agent CLIs/hosts.

An MCP (Model Context Protocol) server that exposes Claude Code-like file and shell tools (bash with background execution, file read/write/edit, glob, grep) over HTTP so an MCP client can use these tools remotely. Includes basic operational hardening such as path validation, timeouts, and result/file size limits.

Provides a local, read-only (per README) MCP server that exposes Confluence data via CData’s JDBC Driver as MCP tools. It runs as a stdio process (suitable for clients like Claude Desktop on the same machine) and supports tool-based table discovery plus SQL SELECT queries through a JSON-RPC tool interface.

Only one skill in the public repo (for now):

Provides a JSON-RPC 2.0 HTTP API for executing shell commands on a server, with a pattern-based command exclusion/validation system (configured via exclude.yaml) and a /context endpoint that serves markdown API documentation.

Provides a bridge between MCP (Model Context Protocol) servers and OpenAI-compatible LLM APIs by translating MCP tool specifications into OpenAI function-calling schemas and mapping tool invocations back to MCP tool executions. Primarily targets OpenAI API usage, with support for other OpenAI-compatible endpoints (e.g., local servers).

Provides a Model Context Protocol (MCP) server (Go) that connects to an Odoo 17 instance via XML-RPC to expose ERP operations as callable MCP tools, primarily for inventory, purchase, and manufacturing (MRP) workflows. Includes optional webhook server configuration (e.g., Discord).

MCP server wrapping the Oracle OCI Visual Builder Studio API, enabling AI agents to programmatically manage Oracle Visual Builder Studio environments — creating, listing, and managing low-code application development environments on Oracle Cloud Infrastructure.

MCP server for Oracle OCI Web Application Acceleration and Security (WAAS) service, enabling AI agents to manage combined CDN acceleration and security policies, configure WAF rules, manage access control lists, and monitor web application protection on Oracle Cloud Infrastructure.

MCP server for the Oracle OCI Web Application Acceleration (WAA) service, providing AI agents the ability to manage CDN policies, caching configurations, and acceleration settings for web applications on Oracle Cloud Infrastructure — distinct from the combined WAAS offering.