mcp 2.0.0 removed `mcp.server.fastmcp`. This repo was pinned to <2
(6723829) to stop a rebuild from crash-looping the container the way
seed-mcp (2026-09-01) and zerto-docs (2026-08-11) did. This lifts the
pin by doing the port — the same mechanical change as
justin/seed-mcp#23 and justin/morpheus-docs#10.
- import: FastMCP -> MCPServer, plus TransportSecuritySettings
- constructor takes no transport options: MCPServer(f"{PRODUCT_NAME}-docs")
- host/port/stateless_http/transport_security are run() kwargs;
`mcp.settings` no longer exists
- requirement becomes plain `mcp>=2,<3` (2.x has no [fastmcp] extra)
@mcp.tool() decorators and all handler signatures are unchanged.
CI now smokes `import docs_mcp.server` twice in both workflows — once
after pip install, once inside the built image — so a green build can
never ship a non-importing container again.
Verified on python:3.12-slim (matches the image):
- tools/list dumped in wire format is BYTE-FOR-BYTE IDENTICAL between
mcp 1.30.0 and 2.2.0, all 10 tools
- streamable-http boots; initialize returns HTTP 200, both from
localhost and with a container-DNS `Host: hvm-docs-mcp:8000` header
(passing host= to run() keeps DNS-rebinding protection off)
- no mcp-session-id response header, i.e. stateless_http is in effect
- stdio boots; initialize + tools/list return 10 tools
- production image builds and imports under mcp 2.2.0; httpx 0.28.1 and
httpx2 2.12.0 coexist as expected
Retrieval is untouched, so no eval numbers are included.
Closes#12
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01QBx2P1VhKQEzJWoZ96QcnH
mcp 2.0.0 moved mcp.server.fastmcp to mcp.server.mcpserver, renamed FastMCP
to MCPServer, and drops the [fastmcp] extra this file requests. With no upper
bound, the next image rebuild resolves to 2.0.0 and the server crash-loops on
import.
That is not hypothetical: it happened to zerto-docs on 2026-08-11 at 02:27
UTC and took the server down until the host was rolled back. This repo shares
the same unpinned line and would fail identically on its next rebuild.
A ceiling, not a migration. The 2.x port is small (the import, the
constructor, and stateless_http moving from the constructor to run()) but it
changes how tool schemas are emitted, which is what decides tool routing, so
it wants a before/after tools/list diff rather than a version bump.
Phase 1: scrape User Manual (8.1.0/.1/.2), Release Notes (8.1.0/.1/.2),
and the unversioned Deployment Guide. Total ~1,160 pages, 9.7 MB markdown.
Discovers via the anonymous JSON API at /hpesc/public/api/document/{docId}:
/toc walks the page tree (for TOC-paginated docs), /render?page=GUID
fetches per-page HTML, /document/{docId} returns the whole body for
single-doc shapes like Release Notes.
Runner converts DITA-source HTML to clean markdown (strips Notices/
Acknowledgments/Abstract boilerplate), writes corpus/<bundle>/<page>.{md,json},
then a finalize pass synthesizes topic_cluster.clustered_topics by GUID
overlap across versions (HPE GUIDs are stable cross-version — confirmed
374/376/376 with 100% overlap on shared pages).
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
justinandClaude Opus 5