MCP server for controlling PKPM (China Academy of Building Research structural design software) from AI agents
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":"pkpm-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.
# pkpm-mcp An **MCP (Model Context Protocol)** server for controlling **PKPM** (structural design software by the China Academy of Building Research) from AI agents such as Claude Desktop, Codex, and Cursor. > **Status: placeholder / name reservation.** > Active development is in progress. This release reserves the package name on PyPI; it is not yet functional. > Track progress at the [GitHub repository](https://github.com/HeisenbergJY1/pkpm-mcp). ## Planned architecture - **Transport**: STDIO (local AI clients) in V1 - **Philosophy**: Workflow-oriented tools, not 1:1 API mappings; stateless server; dry-run human-in-the-loop for write operations ## Platform requirements - Windows 10+ - PKPM (recent versions) - Python 3.10+ ## License MIT
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.