← Back to search

io.github.michael-denyer/hot-memory-mcp

michael-denyer Scanned 12d ago

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

D
55 / 100

Versions

0.4.1latest
first seen Jun 5, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 56

remember
annotations: none low

Store a new memory. Returns the memory ID.

tags string content string category string session_id string memory_type string
recall
annotations: none low

Semantic search with confidence gating and composite ranking. Modes: - 'precision': High threshold (0.8), few results (3), prioritizes similarity - 'balanced': Default settings, good for general use - 'exploratory': Low threshold (0.5), more results (10), diverse ranking Returns memories with confidence level and hallucination-prevention guidance.

mode string limit string query string threshold string memory_type string include_related string expand_relations string
recall_with_fallback
annotations: none low

Recall with automatic fallback through memory types. Tries searching in order: patterns -> project facts -> all types. Stops when min_results are found with medium+ confidence. Use this when you're unsure which memory type contains the answer.

mode string query string min_results string
recall_by_tag
annotations: none low

Get memories with a specific tag.

tag string limit string
forget
annotations: none low

Delete a memory permanently.

memory_id string
list_memories
annotations: none low

List stored memories with pagination.

limit string offset string memory_type string
memory_stats
annotations: none low

Get memory statistics.

preview_consolidation
annotations: none low

Preview memory consolidation without making changes. Shows clusters of similar memories that could be merged. Use this before running actual consolidation to review changes. Args: memory_type: Filter by type (project/pattern/reference/conversation) Returns: Preview of clusters and potential space savings

memory_type string
run_consolidation
annotations: none low

Consolidate similar memories by merging near-duplicates. Finds clusters of semantically similar memories and merges them, keeping the most accessed/valuable one as representative. Args: memory_type: Filter by type (project/pattern/reference/conversation) dry_run: If True (default), only preview without making changes Returns: Consolidation results (clusters processed, memories deleted)

dry_run bool memory_type string
validate_memory
annotations: none low

Mark a memory as validated/confirmed useful. Increases the memory's trust score and records the reason in the trust history. Use this when you verify that a recalled memory is still accurate and helpful. Reasons and their default boosts: - used_correctly: +0.05 (memory was applied successfully) - explicitly_confirmed: +0.15 (user explicitly confirmed accuracy) - cross_validated: +0.20 (corroborated by multiple sources) Trust score is capped at 1.0.

note string boost string reason string memory_id string
invalidate_memory
annotations: none low

Mark a memory as incorrect or outdated. Decreases the memory's trust score and records the reason in the trust history. Use this when you discover that a recalled memory contains inaccurate or outdated information. Reasons and their default penalties: - outdated: -0.10 (information is stale but was once correct) - partially_incorrect: -0.15 (some details are wrong) - factually_wrong: -0.30 (fundamentally incorrect) - superseded: -0.05 (replaced by newer information) - low_utility: -0.05 (not useful in practice) Trust score is floored at 0.0. Memories with very low trust will rank lower in recall results due to trust-weighted scoring.

note string reason string penalty string memory_id string
get_trust_history
annotations: none low

Get the trust adjustment history for a memory. Shows all trust changes with reasons, timestamps, and context. Useful for understanding why a memory's trust score evolved.

limit string memory_id string
seed_from_text
annotations: none low

Seed memories from text content. Parses the content into individual memories (one per paragraph or list item) and stores them. Useful for initial setup or bulk import. Content is split on: - Double newlines (paragraphs) - Lines starting with '- ' or '* ' (list items) - Lines starting with numbers like '1. ' (numbered lists)

content string memory_type string promote_to_hot string
seed_from_file
annotations: none low

Seed memories from a file. Reads the file and extracts memories based on content structure. Supports markdown files (splits on headers and lists) and plain text. Common use: Import from project CLAUDE.md or documentation files.

file_path string memory_type string promote_to_hot string
bootstrap_project
annotations: none low

Bootstrap hot cache from project documentation files. Scans for common project documentation files (README.md, CLAUDE.md, etc.), parses them into memories, and optionally promotes to hot cache. This is ideal for quickly populating the hot cache when starting work on a new codebase. Edge cases handled gracefully: - Empty repo: Returns success with files_found=0 and helpful message - No markdown files: Returns success with message - File read errors: Logged in errors list, continues with other files - Empty files: Skipped silently - Binary files: Skipped with warning - All content already exists: Returns memories_skipped count

tags string root_path string memory_type string file_patterns string promote_to_hot string
link_memories
annotations: none low

Create a typed relationship between two memories. Use this to build a knowledge graph connecting related concepts. Relationships are directional: from_memory -[relation_type]-> to_memory. Examples: - "Python 3.12 features" -[supersedes]-> "Python 3.11 features" - "Auth implementation" -[depends_on]-> "Database schema" - "API endpoint details" -[elaborates]-> "API overview" - "Project notes" -[mentions]-> "PostgreSQL" (entity extraction)

to_memory_id string relation_type string from_memory_id string
unlink_memories
annotations: none low

Remove relationship(s) between two memories. If relation_type is specified, only removes that specific relationship. If not specified, removes all relationships between the two memories.

to_memory_id string relation_type string from_memory_id string
get_related_memories
annotations: none low

Get memories related to a given memory. Returns related memories along with their relationship information. Use this to explore the knowledge graph around a specific concept.

direction string memory_id string relation_type string
relationship_stats
annotations: none low

Get statistics about memory relationships in the knowledge graph.

find_contradictions
annotations: none low

Find memories that may contradict a given memory. Searches for semantically similar memories that could contain conflicting information. High similarity means same topic area, which is where contradictions are likely. Use this after storing a new memory or when validating existing ones.

limit string memory_id string similarity_threshold string
get_contradictions
annotations: none low

Get all memory pairs marked as contradictions. Returns pairs that have been flagged as containing conflicting information. Use resolve_contradiction to handle these.

mark_contradiction
annotations: none low

Mark two memories as contradicting each other. Creates a CONTRADICTS relationship. Use this when you discover that two memories contain conflicting information about the same topic.

memory_id_a string memory_id_b string
resolve_contradiction
annotations: none low

Resolve a contradiction by keeping one memory and handling the other. After resolving: - 'supersedes': Creates SUPERSEDES relationship, weakens trust in discarded - 'delete': Removes the discarded memory entirely - 'weaken': Reduces trust in discarded memory but keeps it

keep_id string resolution string memory_id_a string memory_id_b string
mark_memory_used
annotations: none low

Mark a memory as actually used/helpful after recall. Call this when a recalled memory was useful in your response. Helps improve ranking by tracking which memories are valuable. Args: memory_id: ID of the memory that was useful feedback: Optional feedback (e.g., "helpful", "partially_helpful") Returns: Success response with update count

feedback string memory_id int
retrieval_quality_stats
annotations: none low

Get retrieval quality statistics. Shows which memories are frequently retrieved and actually used. Helps identify high-value and low-utility memories. Args: memory_id: Get stats for specific memory (None for global) days: How many days back to analyze (default 30) Returns: Statistics on retrieval and usage patterns

days int memory_id string
get_sessions
annotations: none low

Get recent conversation sessions. Sessions track which conversations memories originated from. Use this to see conversation history and navigate to specific sessions.

limit string project_path string
get_session
annotations: none low

Get details for a specific session.

session_id string
get_session_memories
annotations: none low

Get all memories from a specific conversation session. Use this to explore what was learned during a particular conversation.

limit string session_id string
cross_session_patterns
annotations: none low

Find content patterns appearing across multiple conversation sessions. Useful for identifying frequently-discussed topics that might warrant promotion to hot cache. Patterns appearing in many sessions are likely important project knowledge. Returns patterns sorted by session count and total accesses.

min_sessions string
set_session_topic
annotations: none low

Set or update the topic for a conversation session. Topics help identify what conversations were about when reviewing session history. Can be auto-detected or manually set.

topic string session_id string
summarize_session
annotations: none low

Summarize a session's key decisions, insights, and action items. Groups session memories by semantic category to extract structured knowledge: - Decisions: Choices made and their rationale - Insights: Lessons learned, antipatterns, landmines, constraints - Action Items: TODOs, bugs, tasks to complete - Context: Background info, conventions, preferences, architecture Use this before end_session() to review what was captured, or anytime to get a structured view of a conversation's key takeaways.

session_id string
end_session
annotations: none low

End a session and consolidate episodic memories. Mirrors human memory consolidation: short-term (episodic) memories that prove valuable get promoted to long-term (semantic) storage. Top episodic memories are selected by salience score (combining importance, trust, access count, and recency). Only memories above the threshold are promoted. Use this at the end of a conversation to preserve valuable learnings.

session_id string promote_top string promote_type string
log_output
annotations: none low

Log an output for pattern mining. Called automatically or manually.

content string session_id string
mining_status
annotations: none low

Show pattern mining statistics.

review_candidates
annotations: none low

Review mined patterns that are ready for promotion.

approve_candidate
annotations: none low

Approve a mined pattern, storing it as a memory and optionally promoting to hot cache.

tags string pattern_id string memory_type string
reject_candidate
annotations: none low

Reject a mined pattern, removing it from candidates.

pattern_id string
bulk_reject_candidates
annotations: none low

Bulk reject multiple mining candidates at once. Provide either pattern_ids (list of specific IDs) OR pattern_type_prefix (e.g., 'entity_' to reject all entity extractions).

pattern_ids string pattern_type_prefix string
run_mining
annotations: none low

Run pattern mining on recent output logs. Extracts patterns (imports, facts, commands, code) from logged outputs and updates the mined_patterns table with occurrence counts. Mining is project-scoped: only logs from the current project are processed.

hours string
hot_cache_status
annotations: none low

Show current hot cache contents, stats, and observability metrics. Returns items sorted by hot_score (highest first), along with: - metrics.hits: Times hot cache resource was read with content - metrics.misses: Times hot cache resource was empty - metrics.evictions: Items removed to make space for new ones - metrics.promotions: Items added to hot cache - effectiveness: Value metrics (hit rate, tool calls saved, most/least used) - avg_hot_score: Average hot score of items (for LRU ranking)

metrics_status
annotations: none low

Get observability metrics for monitoring and debugging. Returns counters and gauges for key operations: - recall: queries, results returned/gated, hot hits, empty results - store: total stores, by type, merges, contradictions - mining: runs, patterns found/new/updated - hot_cache: promotions, demotions, evictions, utilization Useful for debugging performance issues, monitoring usage patterns, and understanding system behavior.

promote
annotations: none low

Manually promote a memory to hot cache for instant recall.

memory_id string
demote
annotations: none low

Remove a memory from hot cache (keeps in cold storage).

memory_id string
pin
annotations: none low

Pin a hot cache memory to prevent auto-eviction. Pinned memories stay in hot cache even when space is needed for new items. Only works on memories already in hot cache.

memory_id string
unpin
annotations: none low

Unpin a memory, making it eligible for auto-eviction from hot cache.

memory_id string
db_maintenance
annotations: none low

Run database maintenance (vacuum, analyze, auto-demote stale). Compacts the database to reclaim unused space, updates query planner statistics, and demotes stale hot memories (if auto_demote is enabled).

run_cleanup
annotations: none low

Run comprehensive cleanup of stale data. Performs all cleanup operations in one call: - Demotes stale hot memories (not accessed in demotion_days) - Expires old pending mining patterns (30+ days without activity) - Deletes old output logs (based on log_retention_days) - Deletes stale memories by type-specific retention policies Use this periodically to keep the database lean. For just database compaction, use db_maintenance() instead.

validate_embeddings
annotations: none low

Check if the embedding model has changed since database was created. If the model or dimension has changed, existing embeddings may be incompatible and memories may need re-embedding. Returns validation status and details about any mismatches.

db_info
annotations: none low

Get database information including schema version and size.

embedding_info
annotations: none low

Get embedding provider and cache information.

audit_history
annotations: none low

Get recent audit log entries for destructive operations. Shows history of operations like delete_memory, demote, maintenance, unlink_memories, etc. Useful for understanding what changed and when. Args: limit: Maximum entries to return (default 50, max 500). operation: Filter by operation type (e.g., "delete_memory", "demote_memory"). Available types: delete_memory, demote_memory, demote_stale, delete_pattern, expire_patterns, cleanup_memories, maintenance, unlink_memories.

limit int operation string
db_rebuild_vectors
annotations: none low

Rebuild all memory vectors with the current embedding model. Use this when: - Switching to a different embedding model - Fixing dimension mismatch errors - Recovering from corrupted vector data This operation: 1. Clears all existing vectors (memories are preserved) 2. Re-embeds every memory with the current model 3. Updates stored model info Warning: This can take time for large databases. Progress is logged.

batch_size string
access_patterns
annotations: none low

Get learned access patterns for predictive caching. When memory_id is provided, shows patterns from that specific memory. Otherwise, shows all learned patterns across all memories. Requires MEMORY_MCP_PREDICTIVE_CACHE_ENABLED=true.

limit string memory_id string min_count string
predict_next
annotations: none low

Predict which memories might be needed next based on access patterns. Uses learned Markov chain of access sequences to predict what memories typically follow after accessing the given memory. Requires MEMORY_MCP_PREDICTIVE_CACHE_ENABLED=true.

limit string memory_id string threshold string
warm_cache
annotations: none low

Pre-warm hot cache with predicted next memories. Promotes predicted memories to hot cache for instant recall. Only promotes memories that aren't already in hot cache. Requires MEMORY_MCP_PREDICTIVE_CACHE_ENABLED=true.

memory_id string
predictive_cache_status
annotations: none low

Get status of the predictive hot cache system. Shows whether predictive caching is enabled, configuration, and learned pattern statistics.

Permissions 4

filesystem low
Server uses filesystem capabilities via: open(), os, pathlib, shutil, tempfile
shell high
Server uses shell capabilities via: subprocess
database medium
Server uses database capabilities via: sqlite3
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 217

low
Tool 'remember' has no annotations annotation_checker · 100%
low
Tool 'recall' has no annotations annotation_checker · 100%
low
Tool 'recall_with_fallback' has no annotations annotation_checker · 100%
low
Tool 'recall_by_tag' has no annotations annotation_checker · 100%
low
Tool 'forget' has no annotations annotation_checker · 100%
low
Tool 'list_memories' has no annotations annotation_checker · 100%
low
Tool 'memory_stats' has no annotations annotation_checker · 100%
low
Tool 'preview_consolidation' has no annotations annotation_checker · 100%
low
Tool 'run_consolidation' has no annotations annotation_checker · 100%
low
Tool 'validate_memory' has no annotations annotation_checker · 100%
low
Tool 'invalidate_memory' has no annotations annotation_checker · 100%
low
Tool 'get_trust_history' has no annotations annotation_checker · 100%
low
Tool 'seed_from_text' has no annotations annotation_checker · 100%
low
Tool 'seed_from_file' has no annotations annotation_checker · 100%
low
Tool 'bootstrap_project' has no annotations annotation_checker · 100%
low
Tool 'link_memories' has no annotations annotation_checker · 100%
low
Tool 'unlink_memories' has no annotations annotation_checker · 100%
low
Tool 'get_related_memories' has no annotations annotation_checker · 100%
low
Tool 'relationship_stats' has no annotations annotation_checker · 100%
low
Tool 'find_contradictions' has no annotations annotation_checker · 100%
low
Tool 'get_contradictions' has no annotations annotation_checker · 100%
low
Tool 'mark_contradiction' has no annotations annotation_checker · 100%
low
Tool 'resolve_contradiction' has no annotations annotation_checker · 100%
low
Tool 'mark_memory_used' has no annotations annotation_checker · 100%
low
Tool 'retrieval_quality_stats' has no annotations annotation_checker · 100%
low
Tool 'get_sessions' has no annotations annotation_checker · 100%
low
Tool 'get_session' has no annotations annotation_checker · 100%
low
Tool 'get_session_memories' has no annotations annotation_checker · 100%
low
Tool 'cross_session_patterns' has no annotations annotation_checker · 100%
low
Tool 'set_session_topic' has no annotations annotation_checker · 100%
low
Tool 'summarize_session' has no annotations annotation_checker · 100%
low
Tool 'end_session' has no annotations annotation_checker · 100%
low
Tool 'log_output' has no annotations annotation_checker · 100%
low
Tool 'mining_status' has no annotations annotation_checker · 100%
low
Tool 'review_candidates' has no annotations annotation_checker · 100%
low
Tool 'approve_candidate' has no annotations annotation_checker · 100%
low
Tool 'reject_candidate' has no annotations annotation_checker · 100%
low
Tool 'bulk_reject_candidates' has no annotations annotation_checker · 100%
low
Tool 'run_mining' has no annotations annotation_checker · 100%
low
Tool 'hot_cache_status' has no annotations annotation_checker · 100%
low
Tool 'metrics_status' has no annotations annotation_checker · 100%
low
Tool 'promote' has no annotations annotation_checker · 100%
low
Tool 'demote' has no annotations annotation_checker · 100%
low
Tool 'pin' has no annotations annotation_checker · 100%
low
Tool 'unpin' has no annotations annotation_checker · 100%
low
Tool 'db_maintenance' has no annotations annotation_checker · 100%
low
Tool 'run_cleanup' has no annotations annotation_checker · 100%
low
Tool 'validate_embeddings' has no annotations annotation_checker · 100%
low
Tool 'db_info' has no annotations annotation_checker · 100%
low
Tool 'embedding_info' has no annotations annotation_checker · 100%
low
Tool 'audit_history' has no annotations annotation_checker · 100%
low
Tool 'db_rebuild_vectors' has no annotations annotation_checker · 100%
low
Tool 'access_patterns' has no annotations annotation_checker · 100%
low
Tool 'predict_next' has no annotations annotation_checker · 100%
low
Tool 'warm_cache' has no annotations annotation_checker · 100%
low
Tool 'predictive_cache_status' has no annotations annotation_checker · 100%
high
Hardcoded API key in michael-denyer-memory-mcp-f81b0ba/tests/test_mining.py auth_checker · 90%
high
Hardcoded API key in michael-denyer-memory-mcp-f81b0ba/tests/test_storage.py auth_checker · 90%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-5h2m-4q8j-pqpj) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-c2jp-c369-7pvx) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-m8x7-r2rg-vh5g) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-mxxr-jv3v-6pgc) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-rcfx-77hg-w2wv) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-rj5c-58rq-j5g5) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-rww4-4w9c-7733) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (GHSA-vv7q-7jx5-f767) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-1364) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-1365) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-2474) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-2475) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-2476) dependency_analyzer · 95%
medium
Vulnerable dependency: fastmcp@3.2,<4 (PYSEC-2026-338) dependency_analyzer · 95%
medium
Vulnerable dependency: sqlite-vec@0.1,<1 (GHSA-vrcx-gx3g-j3h8) dependency_analyzer · 95%
medium
Vulnerable dependency: sqlite-vec@0.1,<1 (PYSEC-2026-1938) dependency_analyzer · 95%
medium
Vulnerable dependency: pydantic@2.0,<3 (GHSA-5jqp-qgf6-3pvh) dependency_analyzer · 95%
medium
Vulnerable dependency: pydantic@2.0,<3 (GHSA-mr82-8j83-vxmv) dependency_analyzer · 95%
medium
Vulnerable dependency: pydantic@2.0,<3 (PYSEC-2021-47) dependency_analyzer · 95%
medium
Vulnerable dependency: pydantic@2.0,<3 (PYSEC-2026-1812) dependency_analyzer · 95%
medium
Vulnerable dependency: loguru@0.7,<1 (GHSA-39ph-wr67-j4xq) dependency_analyzer · 95%
medium
Vulnerable dependency: loguru@0.7,<1 (PYSEC-2022-14) dependency_analyzer · 95%
medium
Vulnerable dependency: click@8.0,<9 (PYSEC-2026-2132) dependency_analyzer · 95%
medium
Vulnerable dependency: fastapi@0.100,<1 (GHSA-8h2j-cgx8-6xv7) dependency_analyzer · 95%
medium
Vulnerable dependency: fastapi@0.100,<1 (PYSEC-2021-100) dependency_analyzer · 95%
medium
Vulnerable dependency: fastapi@0.100,<1 (PYSEC-2024-38) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-462w-v97r-4m45) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-8r7q-cvjq-x353) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-cpwx-vrp4-4pq7) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-fqh9-2qgg-h84h) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-g3rq-g295-4j3m) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-h5c8-rqwp-cp95) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-h75v-3vvj-5mfj) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-hj2j-77xm-mc5v) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (GHSA-q2x7-8rv6-6q7h) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2014-8) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2014-82) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2019-217) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2019-220) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2021-66) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2026-1471) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2026-1473) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2026-1474) dependency_analyzer · 95%
medium
Vulnerable dependency: jinja2@3.0,<4 (PYSEC-2026-1475) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-282v-666c-3fvg) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-29pf-2h5f-8g72) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-37mw-44qp-f5jm) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-37q5-v5qm-c9v8) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-3863-2447-669p) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-4w7r-h757-3r74) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-59p9-h35m-wg4g) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-69w3-r845-3855) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-6rvg-6v2m-4j46) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-9356-575x-2w9m) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-fgcw-684q-jj6r) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-fpwr-67px-3qhx) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-hxxf-235m-72v3) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-jjph-296x-mrcr) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-phhr-52qp-3mj4) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-q2wp-rjmx-x6x9) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-qq3j-4f4f-9583) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-qxrp-vhvm-j765) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-rcv9-qm8p-9p6j) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-v68g-wm8c-6x7j) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (GHSA-wrfc-pvp9-mr9g) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2023-299) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2023-300) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2023-301) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2024-227) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2024-228) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2024-229) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-211) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-212) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-213) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-214) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-215) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-216) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-217) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-218) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2025-40) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1977) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1978) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1980) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1981) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1982) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1983) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1984) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1985) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1986) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1987) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-1988) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-2288) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-2289) dependency_analyzer · 95%
medium
Vulnerable dependency: transformers@4.0,<6 (PYSEC-2026-2290) dependency_analyzer · 95%
info
pyproject.toml metadata manifest_parser · 100%
info
Tool: remember manifest_parser · 90%
info
Tool: recall manifest_parser · 90%
info
Tool: recall_with_fallback manifest_parser · 90%
info
Tool: recall_by_tag manifest_parser · 90%
info
Tool: forget manifest_parser · 90%
info
Tool: list_memories manifest_parser · 90%
info
Tool: memory_stats manifest_parser · 90%
info
Tool: preview_consolidation manifest_parser · 90%
info
Tool: run_consolidation manifest_parser · 90%
info
Tool: validate_memory manifest_parser · 90%
info
Tool: invalidate_memory manifest_parser · 90%
info
Tool: get_trust_history manifest_parser · 90%
info
Tool: seed_from_text manifest_parser · 90%
info
Tool: seed_from_file manifest_parser · 90%
info
Tool: bootstrap_project manifest_parser · 90%
low
Permission: env_vars access detected permission_analyzer · 90%
info
Tool: link_memories manifest_parser · 90%
info
Tool: unlink_memories manifest_parser · 90%
info
Tool: get_related_memories manifest_parser · 90%
info
Tool: relationship_stats manifest_parser · 90%
info
Tool: find_contradictions manifest_parser · 90%
info
Tool: get_contradictions manifest_parser · 90%
info
Tool: mark_contradiction manifest_parser · 90%
info
Tool: resolve_contradiction manifest_parser · 90%
info
Tool: mark_memory_used manifest_parser · 90%
info
Tool: retrieval_quality_stats manifest_parser · 90%
info
Tool: get_sessions manifest_parser · 90%
info
Tool: get_session manifest_parser · 90%
info
Tool: get_session_memories manifest_parser · 90%
info
Tool: cross_session_patterns manifest_parser · 90%
info
Tool: set_session_topic manifest_parser · 90%
info
Tool: summarize_session manifest_parser · 90%
info
Tool: end_session manifest_parser · 90%
info
Tool: log_output manifest_parser · 90%
info
Tool: mining_status manifest_parser · 90%
info
Tool: review_candidates manifest_parser · 90%
info
Tool: approve_candidate manifest_parser · 90%
info
Tool: reject_candidate manifest_parser · 90%
info
Tool: bulk_reject_candidates manifest_parser · 90%
info
No dependency files found for SBOM generation sbom_generator · 100%
info
Tool: run_mining manifest_parser · 90%
info
Tool: hot_cache_status manifest_parser · 90%
info
Tool: metrics_status manifest_parser · 90%
info
Tool: promote manifest_parser · 90%
info
Tool: demote manifest_parser · 90%
info
Tool: pin manifest_parser · 90%
info
Tool: unpin manifest_parser · 90%
info
Tool: db_maintenance manifest_parser · 90%
info
Tool: run_cleanup manifest_parser · 90%
info
Tool: validate_embeddings manifest_parser · 90%
info
Tool: db_info manifest_parser · 90%
info
Tool: embedding_info manifest_parser · 90%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%
info
Tool: audit_history manifest_parser · 90%
info
Tool: db_rebuild_vectors manifest_parser · 90%
info
Tool: access_patterns manifest_parser · 90%
info
Tool: predict_next manifest_parser · 90%
info
Tool: warm_cache manifest_parser · 90%
info
Tool: predictive_cache_status manifest_parser · 90%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
low
Permission: filesystem access detected permission_analyzer · 90%
high
Permission: shell access detected permission_analyzer · 95%
medium
Permission: database access detected permission_analyzer · 90%