Serve promoted Azathoth workflows as Model Context Protocol tools.
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":"azathoth-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.
# Azathoth MCP Azathoth MCP serves promoted [Azathoth](https://github.com/EldritchInc/azathoth) workflows as [Model Context Protocol](https://modelcontextprotocol.io) tools, so an AI client such as Claude Desktop, an IDE or your own agent can call them. Only the workflows an operator lists are offered, each as one tool with the name and description the operator wrote. Every call runs the workflow's active production revision as a recorded, idempotent invocation, and returns the invocation's ID with its result, so what an agent did can be traced to its runs and evidence. It runs over stdio for a local client, or over Streamable HTTP for a team, as an OAuth 2.1 resource server in front of your organization's identity provider. [Serving Workflows Over MCP](https://github.com/EldritchInc/azathoth/blob/main/docs/mcp.md) shows how to expose a workflow, connect Claude Desktop, and serve a team behind your identity provider. Azathoth MCP is released with Azathoth, at the same version, and requires the same minor release of `azathoth-ai`. The design is recorded in [ADR 0111](https://github.com/EldritchInc/azathoth/blob/main/docs/adrs/0111-serve-promoted-workflows-over-mcp.md). ## License MIT. See [LICENSE](https://github.com/EldritchInc/azathoth/blob/main/packages/azathoth-mcp/LICENSE).
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.