Merge pull request 'feat(mcp): migrate to mcp 2.x (MCPServer), lift the mcp<2 pin' (#13) from claude/issue-12 into main

Reviewed-on: #13

.gitea/workflows/image-only.yml

@@ -59,6 +59,9 @@ jobs:
           python -m pip install -q --upgrade pip
           python -m pip install -q -r requirements.txt
 
+      - name: Smoke — server module imports
+        run: python -c "import docs_mcp.server"
+
       - name: Refresh digest history
         # Cheap (few seconds). Without this step, a code-only deploy
         # would ship an increasingly-stale digest history.
@@ -124,6 +127,17 @@ jobs:
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
 
+      - name: Smoke — image must import docs_mcp.server
+        # mcp 2.x renamed mcp.server.fastmcp -> mcp.server.mcpserver, so an
+        # unpinned dep produced a green build that crash-looped in prod
+        # (seed-mcp 2026-09-01, zerto-docs 2026-08-11). Import is
+        # side-effect-free here (lazy singletons), so this needs no
+        # Ollama/Chroma.
+        run: |
+          IMAGE="${{ steps.repo.outputs.owner }}/${{ steps.repo.outputs.name }}"
+          docker run --rm --entrypoint python \
+            "${REGISTRY_PUSH}/${IMAGE}:latest" -c "import docs_mcp.server"
+
       - name: Link container package to this repo
         env:
           GITEA_TOKEN: ${{ secrets.REGISTRY_TOKEN }}

.gitea/workflows/refresh.yml

@@ -77,6 +77,9 @@ jobs:
           python -m pip install -q --upgrade pip
           python -m pip install -q -r requirements.txt
 
+      - name: Smoke — server module imports
+        run: python -c "import docs_mcp.server"
+
       # ---- Phase 1: scrape ---------------------------------------
       - name: Refresh bundle catalog
         run: python -m scrape.bundles
@@ -206,6 +209,18 @@ jobs:
           tags: ${{ steps.meta.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels }}
 
+      - name: Smoke — image must import docs_mcp.server
+        if: steps.commit.outputs.changed == 'true' || inputs.force_build == true
+        # mcp 2.x renamed mcp.server.fastmcp -> mcp.server.mcpserver, so an
+        # unpinned dep produced a green build that crash-looped in prod
+        # (seed-mcp 2026-09-01, zerto-docs 2026-08-11). Import is
+        # side-effect-free here (lazy singletons), so this needs no
+        # Ollama/Chroma.
+        run: |
+          IMAGE="${{ steps.repo.outputs.owner }}/${{ steps.repo.outputs.name }}"
+          docker run --rm --entrypoint python \
+            "${REGISTRY_PUSH}/${IMAGE}:latest" -c "import docs_mcp.server"
+
       - name: Link container package to this repo
         # Idempotent linkage so the package shows under the repo's
         # Packages tab. Gitea's auto-link from the source label is

CLAUDE.md

@@ -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-

docs_mcp/server.py

@@ -25,9 +25,10 @@ import logging
 import os
 import re
 from pathlib import Path
-from typing import Annotated
+from typing import Annotated, Any
 
-from mcp.server.fastmcp import FastMCP
+from mcp.server.mcpserver import MCPServer
+from mcp.server.transport_security import TransportSecuritySettings
 from pydantic import Field
 
 from .usage import TimedCall
@@ -65,13 +66,12 @@ RRF_K = int(os.environ.get("RRF_K", "60"))
 
 
 # ---------------------------------------------------------------------------
-# FastMCP setup.
+# MCPServer setup.
 #
-# stateless_http=True — every request creates an ephemeral session and
-# discards it on return. Critical for production: clients don't get
-# 404 storms when the container is recreated by Watchtower.
+# mcp 2.x moved every transport option (stateless_http, host, port,
+# transport_security, ...) off the constructor and onto run() — see main().
 # ---------------------------------------------------------------------------
-mcp = FastMCP(f"{PRODUCT_NAME}-docs", stateless_http=True)
+mcp = MCPServer(f"{PRODUCT_NAME}-docs")
 
 
 # ---------------------------------------------------------------------------
@@ -1141,14 +1141,22 @@ def main() -> None:
 
     if args.transport == "stdio":
         mcp.run()
-    else:
-        mcp.settings.host = args.host
-        mcp.settings.port = args.port
+        return
+
+    # mcp 2.x: transport options are run() kwargs, and `mcp.settings` is gone.
+    run_kwargs: dict[str, Any] = {"host": args.host, "port": args.port}
+    if args.transport == "streamable-http":
+        # Was a constructor arg under 1.x. Every request creates an ephemeral
+        # session and discards it on return, so clients don't get 404 storms
+        # when Watchtower recreates the container.
+        run_kwargs["stateless_http"] = True
+    if os.environ.get("MCP_DISABLE_DNS_REBINDING_PROTECTION") in {"1", "true", "yes"}:
         # DNS-rebinding protection defaults to localhost-only — disable for
         # container-network DNS hostnames. See PLAN.md "Hosting" notes.
-        if os.environ.get("MCP_DISABLE_DNS_REBINDING_PROTECTION") in {"1", "true", "yes"}:
-            mcp.settings.transport_security.enable_dns_rebinding_protection = False
-        mcp.run(transport=args.transport)
+        run_kwargs["transport_security"] = TransportSecuritySettings(
+            enable_dns_rebinding_protection=False,
+        )
+    mcp.run(transport=args.transport, **run_kwargs)
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1,11 +1,6 @@
 # MCP server
-# Pinned below 2.0: mcp 2.0.0 removed `mcp.server.fastmcp`, which this
-# server imports. The unpinned floor pulled 2.0.0 into a rebuild on
-# 2026-08-11 and crash-looped zerto-docs with
-# "ModuleNotFoundError: No module named 'mcp.server.fastmcp'".
-# 2.0 also drops the [fastmcp] extra. Migrating to the 2.x API is a
-# deliberate piece of work — do not lift this pin without it.
-mcp[fastmcp]>=1.0.0,<2
+# 2.x: no [fastmcp] extra; FastMCP -> MCPServer (see docs_mcp/server.py).
+mcp>=2,<3
 pydantic>=2.0
 httpx>=0.27