Packages

Provides an MCP (Model Context Protocol) server that lets an MCP client query a Typesense instance to perform searches against one or more Typesense collections, exposing a tool (typesense_search) that accepts typical Typesense search parameters and supports filtering/faceting plus pagination.

Provides an MCP (Model Context Protocol) server that exposes WeatherAPI functionality to AI agents, enabling tools/actions to fetch weather data.

Provides a local, read-only MCP server that exposes Workday data via the CData JDBC Driver, wrapping the JDBC driver’s relational/SQL model behind simple MCP tools (get tables/columns and run a SELECT query) over stdio for use with local MCP clients (e.g., Claude Desktop).

An MCP (Model Context Protocol) server implementation for “zstack” that exposes ZStack-related functionality to MCP-compatible AI agents/tools.

A Model Context Protocol (MCP) server that provides programmatic access to Adfin APIs, enabling AI agents to integrate with Adfin's financial management platform for invoice creation, credit control checks, and document uploads.

AI-Infra-Guard (A.I.G) is an AI red-teaming and security assessment platform that runs multiple scanners and evaluations, including OpenClaw security scanning, multi-agent workflow security scanning, MCP server/agent-skills scanning, AI infrastructure/component vulnerability scanning, and LLM jailbreak/prompt security evaluations. It exposes a web UI and a documented set of task-creation APIs (Swagger/docs) for running scans and retrieving results.

fake-gcs-server provides a local/emulated Google Cloud Storage (GCS) compatible server for development and testing, typically exposing an HTTP API that mimics GCS behavior (e.g., buckets/objects) without using the real cloud.

GeoServer is an open-source server for publishing and sharing geospatial data. It exposes geospatial services (notably OGC standards such as WMS/WFS/WCS) and enables configuring data stores and styling to serve maps and geodata over HTTP.

Khoj is a self-hostable “AI second brain” that provides chat and research-style Q&A over local and web/document sources using semantic search and LLMs. It supports multiple frontends (web, desktop/editor integrations) and can run agents and automations.

linkedin-mcp-server is a Model Context Protocol (MCP) server that connects an MCP-compatible LLM/agent to LinkedIn APIs for tasks like people search and profile retrieval, using OAuth 2.0 credentials provided via environment variables.

MassGen is a Python-based multi-agent “scaling”/orchestration framework that runs in a terminal. It coordinates multiple LLM-backed agents to collaboratively solve tasks via parallel work, iterative refinement, convergence/consensus (voting), and real-time visualization (TUI/Web UI). It also supports integration with models/tools and mentions MCP usage for model context.

MCPin10 is a tutorial-style Python project intended to help developers build and run an MCP server (example: Yahoo Finance) and an accompanying agent flow (optionally via Langflow). It relies on mcp[cli] and yfinance, and expects local services like Ollama to be running.

MCP server (Node/JS) intended to expose Bilibili-related capabilities to AI agents via the Model Context Protocol, enabling the agent to call tools for retrieving or interacting with content/metadata from Bilibili.

An MCP (Model Context Protocol) server that connects a client to the Maimemo (墨墨背单词) Open API, exposing MCP tools to query and manage vocabulary-related content such as interpretations, notes, notepads, and phrases, backed by an API token (MAIMEMO_TOKEN).

MetaClaw is a local proxy/agent runtime that sits in front of a user's personal agent (e.g., OpenClaw/CoPaw/etc.) and an OpenAI-compatible LLM API. It injects “skills” into prompts, can summarize sessions into new skills, and (optionally) runs asynchronous RL-style training (e.g., GRPO) on accumulated interaction data. It also includes a scheduler mode (madmax) to defer weight updates to idle/sleep/meeting windows and provides an Anthropic-compatible /v1/messages endpoint for Anthropic-native clients. A CLI (metaclaw) manages setup, config.yaml, starting/stopping, and daemon logging.

An MCP server that exposes tools/resources/prompts for controlling and inspecting a POX (POX SDN controller) environment, including listing datapaths, fetching flow stats, setting flow tables, and appending network insights, plus resources for topology and a network configuration memo.

paladin-mcp-server is an MCP (Model Context Protocol) server package intended to expose one or more Paladin capabilities/tools to MCP-compatible AI agents.

PowerMCP is an open-source collection of MCP servers that let LLM host applications connect to power-system software (e.g., PowerWorld, OpenDSS, and pandapower) to enable simulation/analysis/control workflows in the energy domain.

qu3-app is a Python CLI/client that establishes quantum-safe secure sessions with an MCP server using post-quantum cryptography (Kyber KEM for key establishment and SPHINCS+ for request authentication), then sends encrypted/signed inference and policy-update requests and verifies encrypted/signed responses with server attestations. It also includes a FastAPI mock MCP server for local development/testing.

A Python “agent skill” that helps an AI coding agent plan, generate, and operationalize digital marketing campaigns. It includes utilities for UTM parameter generation/validation/auditing and brand-voice/compliance checking, plus reference materials for content strategy, email/social/SEO/GEO, and analytics/measurement frameworks.