reasoning Static interface comparison

Mnemoverse Memory

0.17.2 0.18.0

REVIEWPending human review

2 schema changes require review.No new authority detected.

View the upgrade review as Markdown

A shareable summary of this comparison for an issue, pull request or ticket. Select the text and copy it.

Tools11 → 11
Added0
Removed0
Schema changes2
Input schema changes0
Output schema changes2
Unclassified schema changes0
Description changes2
New write authority0
New destructive authority0
New unknown authority0
AnalysisREVIEW

INTERFACE DIFF

What changed, tool by tool

Classification from the recorded findings · definitions from the published snapshots

2 tools with recorded changes

  1. memory_readModifiedSchemaDescriptionREVIEWINFO

    What changed

    • memory_read — Schema change: input property added: include_history.
    • memory_read — Output schema: property items changed: items {"additionalPropert… → {"additionalPropert….
    • memory_read: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Code or prompts that read this tool’s results may receive a different shape.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Check consumers of this tool’s output against the new schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    read → read
    Description
    PreviousSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has connected. It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. A correction is a fresh memory_write: it is stored alongside the earlier memory, which is not deleted or hidden, unless it is too close to an existing memory, in which case the write is refused. No MCP deletion tool is exposed; a user can permanently delete an individual personal memory through the REST API or with help from support.
    CurrentSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has connected. It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. A correction is a fresh memory_write. Without supersedes it is stored alongside the earlier memory, which stays as it was, unless it is too close to an existing memory, in which case the write is refused; with supersedes, the earlier memory is marked replaced, is hidden from reads when the account hides replaced memories, and include_history returns it. No MCP deletion tool is exposed; a user can permanently delete an individual personal memory through the REST API or with help from support.

    Input schema

    PropertyPrevious (0.17.2)Current (0.18.0)Change
    include_historynot presentbooleanoptional
    • Added
    9 unchanged entries
    • (schema root)
    • diversity
    • domain
    • exclude_author
    • order_by
    • query
    • since
    • top_k
    • until

    Output schema

    PropertyPrevious (0.17.2)Current (0.18.0)Change
    items › [items] › superseded_bynot presentstringoptional
    • Added
    19 unchanged entries
    • (schema root)
    • items
    • items › [items]
    • items › [items] › author
    • items › [items] › content
    • items › [items] › created_at
    • items › [items] › domain
    • items › [items] › memory_id
    • rooms_not_searched
    • rooms_not_searched › note
    • rooms_not_searched › rooms
    • rooms_not_searched › rooms › [items]
    • rooms_not_searched › rooms › [items] › address
    • rooms_not_searched › rooms › [items] › archived
    • rooms_not_searched › rooms › [items] › name
    • rooms_not_searched › rooms › [items] › role
    • rooms_not_searched › rooms › [items] › room_id
    • rooms_not_searched › rooms › [items] › scope
    • rooms_not_searched › state
    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
  2. memory_writeModifiedSchemaDescriptionREVIEWINFO

    What changed

    • memory_write — Schema change: input property added: supersedes.
    • memory_write — Output schema: property added: superseded.
    • memory_write: description changed.

    Why it could matter

    • Calls or consumers built for the earlier schema may need to change.
    • Code or prompts that read this tool’s results may receive a different shape.
    • Models choose and call tools partly from their descriptions.

    What to verify

    • Validate representative existing tool calls against the new argument schema.
    • Check consumers of this tool’s output against the new schema.
    • Spot-check that agents still select this tool as intended.
    Declared effect
    write → write
    Description
    PreviousStore a long-term memory that persists across sessions and across every AI tool the user has connected to Mnemoverse. Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context.
    CurrentStore a long-term memory that persists across sessions and across every AI tool the user has connected to Mnemoverse. Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context. To correct a memory you have checked is outdated, pass its memory_id in supersedes.

    Input schema

    PropertyPrevious (0.17.2)Current (0.18.0)Change
    supersedesnot presentarray, maxItems=32, minItems=1optional
    • Added
    supersedes › [items]not presentstring, minLength=1
    • Added
    5 unchanged entries
    • (schema root)
    • concepts
    • concepts › [items]
    • content
    • domain

    Output schema

    PropertyPrevious (0.17.2)Current (0.18.0)Change
    supersedednot presentarrayoptional
    • Added
    superseded › [items]not presentstring
    • Added
    5 unchanged entries
    • (schema root)
    • importance
    • memory_id
    • reason
    • stored
    Exact JSON from the published snapshots

    Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.

    Link to this tool
9 tools with no recorded change
  • memory_create_room
  • memory_feedback
  • memory_graph
  • memory_invite_to_room
  • memory_join_room
  • memory_list_recent
  • memory_list_rooms
  • memory_stats
  • vault_list

Evidence and provenance

Static findings
REVIEW from Modelara’s automated analysis of the two declared interfaces. A policy outcome, not a security rating or a runtime test.
Human review
Pending human review. No reviewer decision is recorded for this comparison.
Published evidence
Part of Valyd’s published data generation listed in valyd-data-source.json. Published records are not rewritten.
Show provenance and exact files
Comparison
mnemoverse-mcp-memory-server/0.17.2~0.18.0The published comparison identifier.
Analyzer
modelara v0.1.8Policy version not recorded.Analyzed Nov 16, 2026, 10:44 PM UTC.
Distribution
npm
Previous release
@mnemoverse/mcp-memory-server@0.17.211 tools · published by the registry Nov 11, 2026, 1:05 PM UTCArtifact integritysha512-vPMSV3pKFyxGyOL51/x1CokHR2epusHm9o/Eauxlo1eYj0G2EpSQDyvqKdc/jJrnEBP9YyfxOdTKBiyiRCgvnQ==Interface fingerprintsha256:757990492910f8b6a24577aaf8096f002276b2063ec66ff25f0b4918f1570c70Exact interface snapshot (JSON)
Current release
@mnemoverse/mcp-memory-server@0.18.011 tools · published by the registry Nov 13, 2026, 11:09 PM UTCArtifact integritysha512-P9uXEz00oMHjm5QrblQ6bIQEvDrVDItRO/pdtTLtUizF0piVGDJdRKir1rUmQZo1IPvhY/nvfZxjUjt9Jd5/fA==Interface fingerprintsha256:9b3522859fa37d1b5a5a67ec4f798e6f72d46e4d36cd83634520cb08123b1eb9Exact interface snapshot (JSON)

The integrity value or digest identifies the exact artifact that was inspected; it does not show that the package is safe. The interface fingerprint identifies the declared tools and schemas Modelara recorded for that release.

MODELARA ANALYSIS OUTPUT

Interface findings

Analyzed with Modelara v0.1.8 · Nov 16, 2026

Requires review

2 findings
  • memory_readREVIEWChanged

    Input and output schema changed

    Show details
    • input property added: include_history
    • output property items changed: items {"additionalPropert… → {"additionalPropert…
    Authority
    READREAD
    Authority unchanged
  • memory_writeREVIEWChanged

    Input and output schema changed

    Show details
    • input property added: supersedes
    • output property added: superseded
    Authority
    WRITEWRITE
    Authority unchanged

Informational

2 findings
  • memory_readINFOChanged

    Description changed

    Authority
    READREAD
    Authority unchanged
  • memory_writeINFOChanged

    Description changed

    Authority
    WRITEWRITE
    Authority unchanged
What do these results mean?
PASS
No policy-significant interface change detected.
REVIEW
Interface changes require inspection.
FAIL
A policy-significant change was detected.
INVALID
The comparison could not be evaluated reliably.
← Back to Mnemoverse Memory release history