Synchronous utilities for Model Context Protocol (MCP) integration
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-utils-msgspec","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# mcp-utils-msgspec A synchronous Python utility package for building Model Context Protocol (MCP) servers with `msgspec`.   This package targets **MCP protocol revision `2026-07-28`**. It implements the modern stateless protocol: there is no `initialize` handshake, implicit MCP session, or long-lived HTTP GET stream. ## Features - Required `server/discover` support - Per-request protocol version and client capability metadata - Tools, prompts, resources, simple `{name}` resource templates, and completions - Multi-round-trip input requests and retry metadata - Required `resultType`, cache hints, and server identity metadata - Synchronous, framework-independent request handling - Optional validation of standard Streamable HTTP mirror headers - `msgspec` models for the supported server surface The core returns either one JSON response or no response for a JSON-RPC notification. It does not implement optional request-scoped SSE streams or `subscriptions/listen`, the tasks extension, or optional `x-mcp-header` tool parameter annotations. ## Installation ```bash pip install mcp-utils-msgspec ``` For development: ```bash pip install -e '.[dev]' ``` Python 3.10 or newer and `msgspec` 0.18 or newer are required. Flask and Gunicorn are optional and only needed for the HTTP example. ## Define a server ```python from mcp_utils.core import MCPServer from mcp_utils.schema import GetPromptResult, Message, Role, TextContent mcp = MCPServer( name="weather", version="1.0.0", instructions="Use get_weather for current conditions.", ) @mcp.tool() def get_weather(city: str) -> dict[str, str]: """Return the current conditions for a city.""" return {"city": city, "conditions": "sunny"} @mcp.prompt() def weather_report(city: str) -> GetPromptResult: """Create a prompt asking for a weather report.""" …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.