Hyperia Protocol Overview
Welcome to Hyperia Protocol
Hyperia is the fast, Pythonic way to build Model Context Protocol (MCP) servers and clients.
MCP is a new, standardized method for supplying context, data, and tools to large‑language models. Hyperia removes the boilerplate: create tools, expose resources, define prompts, and more with clean, readable Python.
from hyperia import Hyperia
mcp = Hyperia("Demo 🚀")
@mcp.tool()
def add(a: int, b: int) -> int:
"""Add two numbers"""
return a + b
if __name__ == "__main__":
mcp.run()
Hyperia Protocol & the Official MCP SDK
Two pillars, one ecosystem.
Hyperia Protocol
Official MCP SDK
Maintainer
Hyperia Labs Inc.
MCP Foundation (spec reference impl)
Primary Goal
Developer ergonomics – rapid, high‑level binding of existing code, APIs, and data into MCP.
Specification fidelity – low‑level, one‑to‑one mapping of the core MCP wire format.
Abstraction Level
High: decorators, automatic route mapping, generators (OpenAPI, FastAPI, SQLAlchemy, etc.).
Low: you implement message handlers, transports, serialization manually.
Performance Focus
Async, zero‑copy in‑process calls; optional HTTP layer.
Reference‑grade correctness, not optimised.
Extra Capabilities:
Progress events
Chunk streaming
Auto‑retry/back‑off
Codecs registry
Proxy & composition helpers
ASGI/Starlette adapters
Minimal extras (kept generic to remain specification neutral).
Ideal Users
Product teams, ML engineers, plugin authors needing to expose back‑ends to LLMs fast.
Researchers, alt‑language ports, edge cases needing full control.
Inter‑operability
100% wire‑compatible – Hyperia servers & clients speak the exact MCP frames defined by the spec.
N/A
How They Work Together
Hyperia ≈ "Rails", Official SDK ≈ "C library". Both compile to the same MCP bytes.
Hyperia actually contributes upstream: several transport & context improvements first landed here, then merged into SDK v1.6.
You can mix: implement a custom component in raw SDK and mount it into a Hyperia server, or proxy an SDK server behind Hyperia’s richer transports.
graph LR
subgraph Raw SDK Server
A[tools/call handler]<--MCP-->B(Hyperia Proxy)
end
B-->C(Client Apps)
Migration Path
New project, wants speed
Start with Hyperia; drop to SDK only for exotic needs.
Existing SDK 1.x server
pip install hyperia
→ from hyperia import Hyperia as mcp
Swap imports or proxy via Hyperia.as_proxy(sdk_server)
to gain progress/logging instantly.
Contributing to the spec
Prototype in Hyperia (faster dev cycle), then port minimal patch to SDK.
Version Sync Table
2025‑03‑26 (latest)
1.9.0
2.4.0
OAuth 2.1 auth, chunk streaming
2024‑11‑05
1.7.1
2.2.3
Wildcard resource templates
2024‑07‑18
1.6.0
2.0.0
Initial sync; Hyperia born
Hyperia tracks spec releases within 72 h; patch versions follow semver.
Choosing One (or Both)
If you crave control ➜ official SDK. If you crave velocity ➜ Hyperia. Most teams end up using both: Hyperia for day‑to‑day features, raw SDK for critical, performance‑tuned modules.
llms.txt
llms.txt
This documentation is also distributed in llms.txt format—a lightweight Markdown profile that LLMs can ingest directly.
llms.txt
– a sitemap of every page.llms-full.txt
– the complete docs in a single file (may exceed some model context windows).
Last updated