feat(mcp): migrate to mcp 2.x (MCPServer), lift the <2 pin

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
This commit is contained in:
2026-09-10 22:34:52 -04:00
co-authored by Claude Opus 5
parent e9fc4e841b
commit 841e87c57b
5 changed files with 62 additions and 27 deletions
+10 -7
View File
@@ -68,7 +68,7 @@ Cursor, etc.).
│ ├── index.py # Builds Chroma + BM25
│ └── bm25.py # SQLite FTS5 lexical index
├── docs_mcp/ # Phase 3+ — MCP server
│ ├── server.py # FastMCP + tool definitions
│ ├── server.py # MCPServer + tool definitions
│ └── usage.py # TimedCall telemetry
├── eval/ # Phase 7 — golden-query harness
│ ├── queries.jsonl.example
@@ -139,7 +139,8 @@ need:
- **Lexical store**: SQLite FTS5 (stdlib)
- **Fusion**: Reciprocal Rank Fusion with k=60
- **Transport**: streamable-HTTP in prod, stdio for local dev
- **MCP framework**: FastMCP with `stateless_http=True`
- **MCP framework**: `mcp.server.mcpserver.MCPServer` (mcp 2.x),
with `stateless_http=True` passed to `run()`
- **Container deploy**: Watchtower auto-pull on `:latest`, rollback
via `:<sha12>` pin
@@ -148,7 +149,7 @@ need:
The template uses `PRODUCT_NAME` env var (defaults to `"myproduct"`)
throughout. Set it on first build. References show up in:
- `docs_mcp/server.py` — `FastMCP(f"{PRODUCT_NAME}-docs", ...)`
- `docs_mcp/server.py` — `MCPServer(f"{PRODUCT_NAME}-docs")`
- Collection name (`<product>_docs`)
- BM25 db filename
- Tool names that include the product name (e.g., the `_api_lessons`
@@ -211,10 +212,12 @@ python -m scrape.changelog --history-out corpus/.digest/history.jsonl --history-
ENTIRE batch if any doc exceeds `n_ctx_train=1024`. Truncate docs
to ~2000 chars before sending to rerank. Full chunk text still
goes back to the user; truncation is reranking-only.
- **FastMCP `stateless_http=True`**: critical for production
hosting behind Watchtower auto-updates. Without it, every
container recreate produces a 404 storm from clients with
stale session IDs.
- **`stateless_http=True`**: critical for production hosting
behind Watchtower auto-updates. Without it, every container
recreate produces a 404 storm from clients with stale session
IDs. Under mcp 2.x it is a `mcp.run()` kwarg, not a constructor
arg — along with `host`, `port` and `transport_security`.
`mcp.settings` no longer exists.
- **Runner shell is `/bin/sh` (dash)**: no `${VAR::N}` substring
expansion in workflow scripts. Use `cut`/`awk`/`printf`.
- **Cloudflare 100 MB body cap**: if pushing through a Cloudflare-