MCP Memory Service

Findings (43)

• highHigh. Something risky that needs a close look before you install.
  code-execution issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  code-execution issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  code-execution issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  secrets issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  secrets issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  secrets issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  secrets issue

  Details are available to the maintainer after claiming this listing.
• highHigh. Something risky that needs a close look before you install.
  secrets issue

  Details are available to the maintainer after claiming this listing.
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/git-analyzer.js:33
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/git-analyzer.js:59
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/git-analyzer.js:322
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/git-analyzer.js:328
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/git-analyzer.js:334
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/project-detector.js:201
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/project-detector.js:202
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  claude-hooks/utilities/project-detector.js:203
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Turns off TLS certificate checking, allowing traffic interception.

  scripts/demo/ai_tinkerers_demo.py:78
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Turns off TLS certificate checking, allowing traffic interception.

  scripts/maintenance/cleanup_memories.py:28
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Turns off TLS certificate checking, allowing traffic interception.

  scripts/maintenance/cleanup_memories.py:123
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  scripts/maintenance/cleanup_organize.py:34
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Turns off TLS certificate checking, allowing traffic interception.

  scripts/maintenance/improve_memory_ontology.py:40
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  video/scripts/extract-project-data.ts:46
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  video/scripts/extract-project-data.ts:58
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  video/scripts/extract-project-data.ts:66
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  video/scripts/extract-project-data.ts:113
• mediumMedium. Worth checking, often a vulnerable dependency or a setup problem.
  Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  video/scripts/extract-project-data.ts:118
• lowLow. Minor, or common in normal tools. Shown for information.
  In tests/examples/docs: Runs shell commands. Fine for some tools, but it means the agent can run anything your user can.

  scripts/testing/test_docker_functionality.py:16
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  2 matches in this file

  docs/architecture/search-examples.md:11
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  docs/features/knowledge-graph-dashboard.md:316
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: generic-api-key

  docs/guides/mcp-enhancements.md:229
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  2 matches in this file

  docs/troubleshooting/cloudflare-authentication.md:69
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  examples/README.md:67
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: generic-api-key

  3 matches in this file

  docs/oauth-setup.md:165
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  3 matches in this file

  docs/oauth-setup.md:199
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  3 matches in this file

  docs/cloudflare-setup.md:142
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  3 matches in this file

  docs/quick-setup-cloudflare-dual-environment.md:272
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  docs/troubleshooting/sync-issues.md:111
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: curl-auth-header

  2 matches in this file

  docs/archive/CHANGELOG-HISTORIC.md:1297
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: generic-api-key

  tests/ci/test_hooks_config_secrets_check.sh:56
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: jwt

  tests/ci/test_hooks_config_secrets_check.sh:95
• lowLow. Minor, or common in normal tools. Shown for information.
  Possible example credential in docs/tests: generic-api-key

  tests/test_nli_llm.py:465
• lowLow. Minor, or common in normal tools. Shown for information.
  setuptools@81.0.0: 2 known vulnerabilities

  PYSEC-2026-3447, GHSA-xmj3-9gf7-h52w

  uv.lock
• lowLow. Minor, or common in normal tools. Shown for information.
  No manifest declaring network access and environment variables (agent.json)

Network activity

Tools exposed (28)

• memory_store

  Store new information with optional tags. Accepts two tag formats in metadata: - Array: ["tag1", "tag2"] - String: "tag1,tag2" Use `conversation_id` to bypass semantic deduplication when saving incr

• memory_store_session

  Store a full conversation session as a single memory unit. Use this instead of memory_store when you want to preserve the full context of a multi-turn conversation. All turns are stored together, making session-level retrieval more reliable than storing individual turns separately. Example: { "tur

• memory_search

  Search memories with flexible modes and filters. Primary tool for finding stored information. USE THIS WHEN: - User asks "what do you remember about X", "recall", "find memories" - Looking for past decisions, preferences, context from previous sessions - Need semantic, exact, or time-based search -

• memory_list

  List and browse memories with pagination and optional filters. USE THIS WHEN: - User wants to browse all memories ("show me my memories", "list everything") - Need to paginate through large result sets - Filter by tag OR memory type for categorical browsing - User asks "what do I have stored", "bro

• memory_delete

  Delete memories with flexible filtering. Combine filters for precise targeting. USE THIS WHEN: - User says "delete", "remove", "forget" specific memories - Need to clean up by tag, time range, or specific hash - Bulk deletion with safety preview (dry_run=true) FILTER COMBINATIONS (AND logic when m

• memory_cleanup

  Find and remove duplicate entries

• memory_health

  Check database health and get statistics

• memory_stats

  Get MCP server global cache statistics for performance monitoring. Returns detailed metrics about storage and memory service caching, including hit rates, initialization times, and cache sizes. This tool is useful for:

• memory_update

  Update memory metadata without recreating the entire memory entry. This provides efficient metadata updates while preserving the original memory content, embeddings, and optionally timestamps. Examp

• memory_consolidate

  Memory consolidation management - run, monitor, and control memory optimization. USE THIS WHEN: - User asks about memory optimization, cleanup, or consolidation - Need to check consolidation system health - Want to manually trigger or schedule consolidation - Need to pause/resume consolidation jobs

• memory_ingest

  Ingest documents or directories into memory database. USE THIS WHEN: - User wants to import a document (PDF, TXT, MD, JSON) - Need to batch import a directory of documents - Building knowledge base from existing files SUPPORTED FORMATS: - PDF files (.pdf) - Text files (.txt, .md, .markdown, .rst)

• memory_harvest

  Extract learnings from Claude Code session transcripts. USE THIS WHEN: - End of session — auto-capture decisions, bugs, conventions, learnings - User asks to "harvest" or "extract learnings" from sessions - Building knowledge base from past sessions MODES: - dry_run=true (DEFAULT): Preview candida

• memory_quality

  Memory quality management - rate, inspect, and analyze. ACTIONS: - rate: Manually rate a memory's quality (thumbs up/down) - get: Get quality metrics for a specific memory - analyze: Analyze quality distribution across all memories - maintain: Run maintenance cycle (cleanup + conflicts + stale + qu

• memory_graph

  Memory association graph operations - explore connections between memories. ACTIONS: - connected: Find memories connected via associations (BFS traversal) - path: Find shortest path between two memories - subgraph: Get graph structure around a memory for visualization - extract_entities: Manually e

• memory_conflicts

  List unresolved memory conflicts (contradictory memories detected by similarity analysis)

• memory_resolve

  Resolve a memory conflict by choosing a winner

• mistake_note_add

  Record a mistake pattern for error replay. Tracks what went wrong and the correct action. Auto-increments failure_count for repeated patterns.

• mistake_note_search

  Search mistake notes by semantic similarity. Use before starting a task to check for known pitfalls and past errors.

• mistake_note_update

  Update fields of an existing mistake note. Can update failure_count, error_pattern, context_signature, incorrect_action, or correct_action. Content changes create a new hash (delete + re-store).

• mistake_note_delete

  Delete a mistake note by content hash. Only deletes memories with memory_type='mistake'.

• get_quarantined_memories

  List memories that have been quarantined due to contradicting active beliefs. Use to review flagged memories.

• unquarantine_memory

  Release a memory from quarantine. Use when a quarantined memory is valid (e.g., the contradicted belief was wrong).

• commit_session_legacy

  Record end-of-session learnings from an ephemeral agent. Stores decisions, errors, corrections as structured observations.

• get_bootstrap_profile

  Generate a behavioral bootstrap profile for an ephemeral agent. Requires write scope because it resets session counters when a fresh start is due. For a read-only profile, read memory://agent/{agent_id}/bootstrap instead.

• get_onboarding_guide

  Get integration guide for a specific client type.

• memory_distill

  Extract insights from existing memories via LLM rewriter (batch mode).

• memory_explore

  Explore a knowledge map of entities, with query-scoped chunks per entity (LLM-free). REQUIRES A POPULATED ENTITY GRAPH — returns {"entities": [], "count": 0} otherwise, for every query. Check with memory_graph {"action": "list_entities"}; populate with memory_quality {"action": "maintain", "dry_run

• memory_detail

  Get the full ranked detail for a single entity. USE THIS WHEN: - User drills into one entity from a knowledge map ("tell me more about X") - Need the full ranked list of chunks for an entity plus its related entities Returns: - entity_id, name - chunks: ranked memory chunks (relevance now; composi