diff --git a/CHANGELOG.md b/CHANGELOG.md
index 337a7a1..41dfaac 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -19,7 +19,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ### Bug Fixes
 
-- **MCP server `tool_diary_write` SIGSEGV when EF default differs.** `mcp_server._get_collection` bypassed `ChromaBackend.get_collection` and called `client.get_collection` / `client.create_collection` without `embedding_function=`. ChromaDB 1.x does not persist the EF identity with the collection, so the MCP server's reopen silently bound chromadb's built-in `DefaultEmbeddingFunction` to the collection while the miner / Stop hook ingest path bound `mempalace.embedding.get_embedding_function()`. On bleeding-edge interpreters (python 3.14 + chromadb 1.5.x on Apple Silicon) the default's lazy ONNX provider selection could SIGSEGV the host process on first `col.add()`, killing the MCP stdio server and leaving every subsequent tool call returning `Connection closed` until Claude Code was relaunched. `_get_collection` now resolves the EF via `mempalace.embedding.get_embedding_function` and passes it into both reopen branches, matching the miner/backend path. (#1299, follow-up to #1262 / #1289)
+- **MCP server `tool_diary_write` SIGSEGV when default EF provider differs.** `mcp_server._get_collection` bypassed `ChromaBackend.get_collection` and called `client.get_collection` / `client.create_collection` without `embedding_function=`. ChromaDB 1.x persists the EF *identity* (its `name()`) with the collection but not the EF *instance/configuration*, so the MCP server's reopen silently bound chromadb's built-in `DefaultEmbeddingFunction` — its `name()` matches `mempalace.embedding`'s spoofed `"default"` so the identity check passes, but its provider list is chromadb's default rather than the user's resolved device. The miner / Stop hook ingest path routes through the backend helper and binds the configured EF instead. On bleeding-edge interpreters (python 3.14 + chromadb 1.5.x on Apple Silicon) the default provider selection could SIGSEGV the host process on first `col.add()`, killing the MCP stdio server and leaving every subsequent tool call returning `Connection closed` until Claude Code was relaunched. `_get_collection` now reuses `ChromaBackend._resolve_embedding_function()` on the reopen branches that actually open a collection (warm-cache reads stay zero-cost), matching the miner/backend path. (#1299, follow-up to #1262 / #1289)
 - **Cross-wing topic tunnels for hyphenated dir names.** `mempalace init` recorded the `topics_by_wing` registry key under the raw directory name (e.g. `mempalace-public`), while `mempalace.yaml`'s `wing` field used the lower-cased + separator-collapsed slug (`mempalace_public`). At mine time the miner read the slug from the yaml and missed the registry, so `_compute_topic_tunnels_for_wing` returned `0` silently. Real-world: any project whose folder contained a hyphen or space lost every topic tunnel. Now both call sites route through a shared `normalize_wing_name()` in `config.py`. (#1194, follow-up to #1180)
 - **CLI `mempalace search` retrieval quality.** The CLI was using pure ChromaDB cosine distance with no BM25 rerank, so drawers containing every query term but embedding as noise (directory listings, diff output, shell logs) scored `Match: 0.0` alongside genuinely irrelevant results with no way to tell them apart. Wired the CLI through the same `_hybrid_rank` the `mempalace_search` MCP tool already used, and surfaced both `cosine=` and `bm25=` scores in the output so users see which component of the match is firing. MCP search was unaffected; this fixes the human-facing CLI parity gap.
 - **Legacy-palace distance-metric warning.** CLI search now detects palaces created before `hnsw:space=cosine` was consistently set and prints a one-line notice pointing at `mempalace repair`. Without the warning such palaces silently used L2 distance, under which the similarity display floored every result to `Match: 0.0`. New palaces mined today already set cosine correctly and now have invariant tests pinning that behavior so future refactors can't silently regress it. (#1179)
diff --git a/mempalace/mcp_server.py b/mempalace/mcp_server.py
index faa024c..13654f6 100644
--- a/mempalace/mcp_server.py
+++ b/mempalace/mcp_server.py
@@ -66,7 +66,6 @@ from .backends.chroma import (  # noqa: E402
     _pin_hnsw_threads,
     hnsw_capacity_status,
 )
-from .embedding import get_embedding_function  # noqa: E402
 from .query_sanitizer import sanitize_query  # noqa: E402
 from .searcher import search_memories  # noqa: E402
 from .palace_graph import (  # noqa: E402
@@ -279,23 +278,25 @@ def _get_collection(create=False):
     global _collection_cache, _metadata_cache, _metadata_cache_time
     try:
         client = _get_client()
-        # ChromaDB 1.x does not persist the embedding function with the
-        # collection, so a reader/writer that omits ``embedding_function=``
-        # silently gets the chromadb-built-in default. On bleeding-edge
+        # ChromaDB 1.x persists the EF *identity* (its ``name()``) with the
+        # collection but not the EF *instance/configuration*. So a reader or
+        # writer that omits ``embedding_function=`` silently gets chromadb's
+        # built-in ``DefaultEmbeddingFunction`` — its ``name()`` matches the
+        # one we spoof in ``mempalace.embedding`` (both report ``"default"``,
+        # the identity check passes), but the *provider list* is chromadb's
+        # default rather than the user's resolved device. On bleeding-edge
         # interpreters (#1299: python 3.14 + chromadb 1.5.x on Apple Silicon)
-        # the default's lazy ONNX provider selection can SIGSEGV the host
-        # process on first ``col.add()``. The miner / Stop hook ingest path
-        # avoids this because it routes through ``ChromaBackend.get_collection``
-        # which resolves the EF via ``mempalace.embedding.get_embedding_function``.
-        # The MCP server bypassed that abstraction; mirror its behaviour so
-        # ``tool_diary_write`` / ``tool_add_drawer`` get the same EF as mining.
-        try:
-            ef = get_embedding_function()
-        except Exception:
-            logger.exception("Failed to build embedding function; using chromadb default")
-            ef = None
-        ef_kwargs = {"embedding_function": ef} if ef is not None else {}
+        # that default provider selection can SIGSEGV the host process on
+        # first ``col.add()``. The miner / Stop hook ingest path avoids this
+        # because it routes through ``ChromaBackend.get_collection``, which
+        # resolves the EF via ``ChromaBackend._resolve_embedding_function``;
+        # the MCP server bypassed that abstraction. Resolve the EF inside the
+        # branches that actually open a collection so warm-cache reads stay
+        # zero-cost. Reuse the backend helper so the two call sites can't
+        # drift on logging or fallback semantics.
         if create:
+            ef = ChromaBackend._resolve_embedding_function()
+            ef_kwargs = {"embedding_function": ef} if ef is not None else {}
             # hnsw:num_threads=1 disables ChromaDB's multi-threaded ParallelFor
             # HNSW insert path, which has a race in repairConnectionsForUpdate /
             # addPoint (see issues #974, #965). Set via metadata on fresh
@@ -325,6 +326,8 @@ def _get_collection(create=False):
             _metadata_cache = None
             _metadata_cache_time = 0
         elif _collection_cache is None:
+            ef = ChromaBackend._resolve_embedding_function()
+            ef_kwargs = {"embedding_function": ef} if ef is not None else {}
             raw = client.get_collection(_config.collection_name, **ef_kwargs)
             _pin_hnsw_threads(raw)
             _collection_cache = ChromaCollection(raw)