github doobidoo/mcp-memory-service v12.11.0

one hour ago

Security

v12.11.0 fixes GHSA-989p-hfjf-q97q. With a per-store write grant such as write:projectA, memory_store could write to and supersede memories in another store. Affected: 12.4.0 to 12.10.0, on the backends that confine by store (sqlite-vec and hybrid). Setting MCP_AUTO_EXTRACT_DEFAULT=false is not a mitigation, because an explicit auto_extract argument wins. Upgrading is the fix.

Special Thanks to RISCON Labs (@RISCON-Labs, https://www.risconlabs.com) for reporting it. The conflict-detection item in the same entry was found separately, by the maintainer.

Also in this release: the dashboard offers the openai-compatible quality provider (#1668, KshitijKasodkar).

Security

  • A per-store write grant could write to and supersede memories in another store through memory_store (GHSA-989p-hfjf-q97q, reported by RISCON Labs, @RISCON-Labs).
    With auto_extract=true, handle_store_memory stored the memory in the granted store but ran auto-capture without it. AutoCaptureService.capture(), SessionHarvester._try_evolve() and MemoryService.evolve_memory() took no store, so the extracted candidates were compared with the default store, replaced a similar memory there, or were inserted there. A client holding only write:projectA could overwrite default. The NLI contradiction check on store (MCP_NLI_ON_STORE, inline and background) had the same gap: it compared a memory with the default store whatever store it was written to, linked the two with a contradicts edge and reported the hit count to the caller. It also missed contradictions inside a named store for the same reason. Conflict detection on store, which runs on every write without any flag, compared the new memory with every store as well and tagged a near-identical memory in another store conflict:unresolved, with contradicts edges between the two; it is confined to the store of the write now. store is now passed down all of these paths, and evolve_memory() refuses a hash from another store by itself. Setting MCP_AUTO_EXTRACT_DEFAULT=false was never a mitigation: an explicit auto_extract argument wins. Affected: 12.4.0 to 12.10.0, on backends that confine by store (sqlite-vec, hybrid). On Cloudflare and Milvus a per-store grant never authorized these calls; there, auto-capture for a named store now stores candidates in that store without evolving existing ones.

Added

  • The dashboard offers the openai-compatible quality provider (#1668, KshitijKasodkar).
    The Quality tab and the environment listing offered local, groq, gemini, auto, none, so
    the provider behind Ollama, vLLM, MLX-LM, LiteLLM and fm serve could not be picked, and
    MCP_QUALITY_AI_BASE_URL, MCP_QUALITY_AI_MODEL and MCP_QUALITY_AI_API_KEY were not
    listed. They are now, with the API key masked like MCP_MILVUS_TOKEN. Gemini is no longer
    offered while _score_with_gemini raises NotImplementedError. Saving openai-compatible
    from the Quality tab is refused until the base URL and model are set, the same way groq
    needs GROQ_API_KEY, so the restart cannot come back to a server that fails validation.

Fixed

  • Hybrid sync progress was shown nowhere on the dashboard (#2002, InlitX).
    handleSyncProgress() and handleSyncCompleted() wrote the sync_progress and
    sync_completed events into a #syncStatus element that index.html no longer has,
    a manual sync raised one toast per progress event, and every finished sync raised one
    more. Hybrid sync now reports to the status island as its own "Cloud sync" source: a
    rising percentage while it runs, a confirmation that steps back to "Synced" when it
    ends, and a failure that stays until the next sync status. The ten-second
    GET /api/sync/status poll maps synced, syncing, pending, error and paused to
    the island without overwriting a measured percentage or a confirmation, and a backend
    without hybrid sync reports nothing.
  • The session-start hook reported every install as 10.13.0 (outdated) (#2019).
    readLocalVersion() in claude-hooks/utilities/version-checker.js took the first
    __version__ literal in __init__.py, which is only the fallback for a missing
    _version.py. It now reads _version.py first and keeps __init__.py as the
    fallback.
  • The dashboard status island labeled its reconnect action "Refresh" (#2010,#2022 Shivraj-G).
    The island was built without catalog keys of its own, so it borrowed analytics.refresh,
    manage.ontology.column.detail and modal.close. The reconnect action therefore read
    "Refresh" instead of "Reconnect", and the connection row in the panel had no name. The
    island now has its own keys (island.reconnect, island.details, island.dismiss,
    island.source.connection) in all eleven catalogs, and the connection row is named
    "Live updates".
  • scripts/maintenance/sync_status.py no longer carries Cloudflare credentials. It fell back to a hardcoded API token, account ID and D1 database ID when the environment did not set them, so the token sat in the public repository since January. The fallbacks are gone and the script exits with a clear message naming the missing variables. CI now runs gitleaks over each pull request's own commits, and the pre-commit hook scans staged changes when gitleaks is installed.
  • time_expr="day before yesterday" now selects the day before yesterday. parse_time_expression matched the word "yesterday" inside the phrase and returned yesterday's window, so memory_search, the HTTP time search and recall silently returned the wrong day. extract_time_expression also left "day before" in the search text. Both now treat the whole phrase as two days ago, with or without a daypart.

Internal

  • A request to take over an assigned issue went unnoticed, and so did a claim with a condition attached (#2020).
    On #1668 a contributor wrote "I would like to take this if ..." on an issue whose
    assignee had been silent for a week. Claim Pending logged "comment is not a claim":
    the phrase had to end its clause, and an assigned issue was never labelled anyway. A
    claim followed by if, unless or once now counts, and a prose claim on an issue
    assigned to someone else gets claim-pending. The assignee's own comment and a bare
    /claim do not. A declined takeover leaves the label for manual removal.
  • storage/mixins/retrieve.py and storage/shared.py join GUARDED_MODULES (#2026, part of #1146, massimiliano1991).
    In retrieve.py the two f-string logger calls (result count with the sanitised
    query, result count with the tag list) are lazy %d/%s calls, the tag list goes
    through _sanitize_log_value as storage/mixins/delete.py already does, and the
    tag count and a rejected tag's type name are read into their own names before they
    are logged. In shared.py the exc of _safe_json_loads is wrapped: the text it
    parses is the metadata column read back off a row. A sample test pins the three forms.
  • consolidation/consolidator.py, decay.py, health.py, insights.py, and scheduler.py join GUARDED_MODULES (#1146).
    All f-string logger calls are converted to lazy %-style; memory hashes (content_hash), exception values (e, exc, errors, msg) and config paths (db_path) are wrapped with _sanitize_log_value; ternary message selects are split into plain if/else branches; insights.py gains the _sanitize_log_value import. A sentinel test pins the wrapper requirement for content hashes, exception values, and f-string logger calls across the five modules.
  • web/api/health.py sanitizes its logged exception (#1146).
    When the embedding integrity check behind /api/health/detailed fails, the
    exception is now passed through _sanitize_log_value, like the same message
    in utils/health_check.py, so a newline in it cannot forge a log line. The
    module is added to GUARDED_MODULES.

Don't miss a new mcp-memory-service release

NewReleases is sending notifications on new releases.