Packages

> **Turn your product idea into a production-ready development plan in minutes**

fast-agent is a Python CLI-first framework for interacting with LLMs and building coding agents, workflows, and evaluation pipelines. It supports MCP servers/clients (including stdio and streamable HTTP/SSE transports), shell-mode, interactive TUI prompts, and Python agent definitions (decorator-based) that can call MCP tools and chain workflows. It also includes MCP OAuth (PKCE) integration and optional MCP ping support.

FieldFlow loads an OpenAPI 3.0 spec (JSON/YAML), generates FastAPI endpoints that act as a proxy to an upstream REST API, and supports field-slicing of responses via an optional `fields` selector. It can also expose the generated tools through an optional MCP server for LLM client tool use.

A content-addressable protocol for universal food data.

A content-addressable protocol for universal food data.

Fusio is a self-hosted API management platform that sits between data sources/microservices and API consumers. It provides routing and gateway functionality, authentication, documentation, and automated SDK generation; it also supports AI-agent tool integration via custom backend logic and native MCP support.

<div align="center">

[](https://gitingest.com)

MCP server that enables AI agents to autonomously execute 150+ cybersecurity tools across network recon, web app testing, auth cracking, binary analysis, cloud security, and CTF/forensics. Features 12+ specialized AI agents for orchestrating complex security workflows.

MCP server built on akshare that provides stock and cryptocurrency data query and analysis functions. Supports A-share, Hong Kong, and US stock markets plus crypto data from OKX and Binance. Includes stock search, pricing, financial indicators, market overview (limit-up boards, capital flows), historical data with technical indicators, and financial news.

MCP server that lets LLMs dynamically discover and query any GraphQL API by introspecting its schema, executing queries, and optionally executing mutations against a configured endpoint.

An MCP (Model Context Protocol) server that exposes Oura API data via MCP tools, allowing clients to fetch sleep, readiness, and resilience data for today or for arbitrary ISO date ranges using an Oura personal access token.

mcp-server-go is a Go library for implementing an MCP (Model Context Protocol) server. It provides abstractions to define MCP tools/resources/prompts and to serve the MCP server over stdio via an implementation of the MCP protocol.

An MCP server (Go binary) that ingests Atlassian Jira board issue transition history, reconstructs workflow semantics, and serves Monte-Carlo/flow diagnostics to AI agents (e.g., forecasting completion dates, capacity/bottleneck analysis, stability/predictability via control charts).

Movies MCP Server is an MCP (Model Context Protocol) server that manages a PostgreSQL-backed movie database, exposing tools for movie and actor CRUD, linking/unlinking cast, search (multi-criteria, by decade, by rating range), bulk import, recommendations, and director career analysis. It also provides MCP resources for returning full database stats and base64-encoded poster images.

Archived TypeScript library that converts Swagger/OpenAPI (v2.0, v3.0, v3.1) documents into type-safe schemas suitable for LLM function calling. It normalizes specs through an “emended” OpenAPI v3.1 intermediate format, and includes runtime validation (via typia integration) to validate/repair LLM-generated arguments. It also references MCP-related integration and adapters for common LLM tooling ecosystems.

> Battle-tested execution playbooks that give any AI agent the exact commands, APIs, and patterns it needs — cutting token usage by **95–98%** and making local models as capable as GPT-4.

DMARC Report Parser and Dashboard

PIC (Provenance & Intent Contracts) is a Python library/CLI and integration set that validates structured “action proposals” for AI agents, enforcing fail-closed checks on intent/impact, provenance trust, and evidence (hash/signature) before allowing tool execution.

Provides a Model Context Protocol (MCP) server that lets AI assistants connect to a Prometheus server, discover metrics/targets, and run PromQL instant and range queries via MCP tools. Configuration is primarily done through environment variables (PROMETHEUS_URL and optional credentials/tokens).