Stateless Model Context Protocol (MCP) server for Django, built on the 2026-07-28 spec.
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":"django-stateless-mcp","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.
# django-stateless-mcp  [](https://django-stateless-mcp.readthedocs.io/) An [MCP](https://modelcontextprotocol.io) (Model Context Protocol) server is how AI agents — Claude Code, ChatGPT, and the assistants built on them — connect to your application in a controlled way: they see and call only the tools you choose to expose, under the permissions you enforce. As your users lean on AI for more of their work, it pays to be ready to accommodate their agents without loosening the protections Django already gives your data and infrastructure — and that is what this package is for. django-stateless-mcp is a stateless MCP server for Django, built on the [**2026-07-28** spec](https://modelcontextprotocol.io/specification/2026-07-28). An MCP endpoint becomes an ordinary Django view — no sessions, no SSE, no sticky routing, and no dedicated single-process service. * [GitHub](https://github.com/Streamlined-Analytics/django-stateless-mcp/) | [PyPI](https://pypi.org/project/django-stateless-mcp/) | [Documentation](https://django-stateless-mcp.readthedocs.io/) * Created by [Ben Atkinson](https://streamlinedanalytics.co.uk) | GitHub [@BenA-SA](https://github.com/BenA-SA) * MIT License ## Why use this * **Your MCP server is an ordinary Django view** — same deployment, same middleware, same monitoring, and tools call your models and business logic directly. No separate MCP service to build, secure, and operate. * **It scales like the rest of your Django app** — any worker on any instance can serve any request, including an elicitation answer. See [Why stateless](https://django-stateless-mcp.readthedocs.io/en/stable/why-stateless/) for what changed on 2026-07-28 to make that possible. * **Tools can ask the user questions** — fill in missing form fields, or require explicit confirmation before an u…
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.