// SCAN REPORT

Enhanced Knowledge Graph Memory Server

Q: Can an AI agent delete data through the Enhanced Knowledge Graph Memory Server MCP server?

Yes. The Enhanced Knowledge Graph Memory Server server exposes 22 destructive tools including adaptive_reduce_memories, cache_clear, clear_expired_memories. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

Q: How do I prevent bulk modifications through Enhanced Knowledge Graph Memory Server?

The Enhanced Knowledge Graph Memory Server server has 53 write tools including accept_decision, add_exclusion_rule, add_heuristic. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Enhanced Knowledge Graph Memory Server.

Q: How many tools does the Enhanced Knowledge Graph Memory Server MCP server expose?

225 tools across 4 categories: Destructive, Execute, Read, Write. 140 are read-only. 85 can modify, create, or delete data.

Q: How do I enforce a policy on Enhanced Knowledge Graph Memory Server?

Register the Enhanced Knowledge Graph Memory Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

225 tools. 85 can modify or destroy data without limits.

22 destructive tools with no built-in limits. Policy required.

Last updated: 16 Jul 2026

85 can modify or destroy data

140 read-only

225 tools total

Community server · catalogue entry checked 16/07/2026

How to control Enhanced Knowledge Graph Memory Server ↓

TOOL MAP

What Enhanced Knowledge Graph Memory Server exposes to your agents

Read (140) Write / Execute (63) Destructive / Financial (22)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Enhanced Knowledge Graph Memory Server tools

Destructive · High clear_expired_memories This tool permanently deletes data without user confirmation per operation—it removes all expired memories in batch. Destructive · High delete_entities This tool permanently removes entities from persistent storage without apparent undo/recovery mechanism. Destructive · High delete_observations This tool permanently removes observations from the knowledge graph storage. Destructive · High delete_relations This tool permanently removes relations from a knowledge graph that is explicitly described as having 'persistent knowledge graph storage'.

85 of Enhanced Knowledge Graph Memory Server's 225 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Enhanced Knowledge Graph Memory Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Enhanced Knowledge Graph Memory Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "adaptive_reduce_memories": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "accept_decision": {
    "limits": [
      {
        "counter": "accept_decision_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "adaptive_retrieve": {
    "limits": [
      {
        "counter": "adaptive_retrieve_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Enhanced Knowledge Graph Memory Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ENHANCED KNOWLEDGE GRAPH MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 225 Enhanced Knowledge Graph Memory Server tools

DESTRUCTIVE 22 tools

Destructive adaptive_reduce_memories Adaptively reduce a set of memories until their cognitive load falls below the configured threshold by removin Destructive cache_clear v12.5.0 \u2014 Bust all four global search caches. Idempotent; safe after manual graph edits to drop stale res Destructive clear_expired_memories Remove all working memories that have exceeded their TTL. Complements get_expired_entities (which lists but do Destructive clear_heuristics v2.1.0 \u2014 Drop every heuristic (across all entities of type Destructive clear_project_context v2.1.0 \u2014 Wipe the four arrays (facts/conventions/commands/glossary) for projectId; keeps the entity. Destructive delete_entities Delete multiple entities from the knowledge graph Destructive delete_observations Delete specific observations from entities Destructive delete_relations Delete multiple relations from the knowledge graph Destructive delete_saved_search Delete a saved search Destructive deregister_ref Remove a stable alias (ref) from the RefIndex Destructive forget_memory Forget (delete) observations matching the given content. Tries exact match first; falls back to semantic searc Destructive forget_weak_memories Bulk-delete memories that fell below a decay threshold. Unlike forget_memory (content match) or archive_entiti Destructive invalidate_entity \u03B7.4.4 \u2014 Mark an entity as no longer valid by setting validUntil. Idempotent. Does not delete the ent Destructive rbac_revoke_role \u03B7.6.1 \u2014 Remove a specific role assignment. Matching is by agentId + role + resourceType (exact, incl Destructive remove_exclusion_rule v2.1.0 \u2014 Drop an exclusion rule by id. Does NOT restore previously deleted memories \u2014 the contract i Destructive remove_heuristic v2.1.0 \u2014 Drop a heuristic by id. Destructive remove_project_command v2.1.0 \u2014 Remove a command by name. Returns true if found. Destructive remove_project_convention v2.1.0 \u2014 Remove a single convention. Returns true if found. Destructive remove_project_fact v2.1.0 \u2014 Remove a single fact. Returns true if found. Destructive remove_project_glossary_term v2.1.0 \u2014 Remove a glossary entry by term. Returns true if found. Destructive remove_tag_alias Remove a tag alias Destructive remove_tool_affordance v2.1.0 \u2014 Drop a tool-affordance record by toolName.

EXECUTE 10 tools

Execute consolidate_session Run the full ConsolidationPipeline on a session: promote working memory, merge duplicates, summarize, and extr Execute dream_run_now Run a single dream cycle immediately. Returns detailed per-phase results. Execute dream_start Start the DreamEngine background memory maintenance. Runs 8 phases (temporal anchoring, freshness sweep, entro Execute dream_stop Stop the DreamEngine background process. Execute end_session End a session and trigger failure distillation if the session outcome was a failure Execute parse_adr_markdown v2.1.0 \u2014 Parse a hand-written or previously-exported ADR markdown into a DecisionInput shape (static; no Execute run_consolidation_now Run a consolidation cycle on demand, independently of the scheduled interval Execute run_decay_cycle Run a single pass of time-based importance decay across all agent memories. Returns count of decayed and forgo Execute start_consolidation Start the background consolidation scheduler that periodically deduplicates and merges memories Execute stop_consolidation Stop the background consolidation scheduler

WRITE 53 tools

Write accept_decision v2.1.0 \u2014 Transition a proposed decision to accepted. Returns one of: accepted | already-accepted | not-fo Write add_exclusion_rule v2.1.0 \u2014 Add a content-pattern exclusion rule (do_not_remember). Hard-deletes existing matches (per Write add_heuristic v2.1.0 \u2014 Register a new condition\u2192action heuristic. Storage-backed; default confidence 0.5. Pass an Write add_observations Add new observations to existing entities in the knowledge graph Write add_procedure 3B.4 \u2014 Persist a new procedural memory (executable how-to sequence). Steps are ordered (1-indexed) with o Write add_tag_alias Add a tag alias (synonym mapping) Write add_tags Add tags to an entity Write add_tags_to_multiple_entities Add the same tags to multiple entities at once Write add_working_memory Create a TTL-based short-term working memory entry scoped to a session. Working memories auto-expire and can b Write archive_entities Archive old or low-importance entities Write compress_graph Compress the graph by merging similar entities Write configure_distillation Configure the distillation pipeline policy (default, noop, or none) that filters memories before context forma Write create_artifact Create an artifact entity (tool output, code snippet, API response, etc.) with a stable auto-generated ref Write create_entities Create multiple new entities in the knowledge graph. Supports v1.6 freshness (ttl/confidence), v1.8 project sc Write create_relations Create multiple new relations between entities in the knowledge graph. Relations should be in active voice Write diary_write Write a timestamped diary entry for a specialist agent. Each agent gets its own persistent diary (entity: diar Write distill_failure Distill lessons from a failed session by tracing the causal chain and extracting actionable insights Write enable_entropy_filter Enable or disable the Shannon entropy gate that drops low-information memories during consolidation Write export_decision_as_adr_markdown v2.1.0 \u2014 Render a stored decision as ADR-format markdown ( title, Status, Context, Decision, Consequences Write export_graph Export knowledge graph in various formats with optional brotli compression and streaming for large graphs. Sup Write import_graph Import knowledge graph from various formats Write ingest Ingest pre-normalized conversation data into the knowledge graph. Chunks messages by exchange pairs (user+assi Write invalidate_relation Mark a relation as no longer valid. Sets the validUntil timestamp on the matching active relation. Use for tem Write merge_entities Merge multiple entities into one Write merge_tags Merge two tags into a target tag across all entities Write move_entity Move an entity to a new parent Write normalize_observations Normalize entity observations by resolving pronouns and anchoring relative dates. Improves search matching qua Write promote_working_memory Promote a working memory entry to long-term episodic or semantic storage Write rbac_assign_role \u03B7.6.1 \u2014 Grant a role to an agent. Roles: reader (read), writer (read+write), admin (read+write+delet Write refresh_entity Reset freshness for an entity by updating its creation timestamp to now and resetting confidence to 1.0 Write register_agent Register an agent for multi-agent operations with identity metadata. Unlike set_agent_role (which applies a ro Write register_ref Register a stable alias (ref) pointing to an entity name in the RefIndex for O(1) lookups Write reject_decision v2.1.0 \u2014 Transition a proposed decision to rejected with a reason. Returns rejected | already-rejected | Write remove_tags Remove tags from an entity Write replace_tag Replace a tag with a new tag across all entities Write resolve_agent_conflict Resolve a conflict between two agent memories using a specified strategy Write rollback_operation Reverse a specific committed operation using its audit entry ID (restores entity to before-snapshot) Write save_search Save a search query for later reuse Write session_checkpoint Create a checkpoint snapshot of the current session state for later restore Write session_end End an agent session via AgentMemoryManager with summary generation and working memory promotion. Unlike end_s Write session_restore Restore a session from a previously created checkpoint Write session_start Start a new agent session via AgentMemoryManager. Tracks session lifecycle, enables working memory, and suppor Write set_agent_role Apply a built-in role profile (researcher, planner, executor, reviewer, coordinator) to adjust salience weight Write set_entity_parent Set the parent of an entity for hierarchical organization Write set_governance_policy Set the active governance policy controlling which write operations (create, update, delete) are permitted for Write set_importance Set the importance score of an entity (0-10) Write set_memory_visibility Set the visibility of a memory entity for multi-agent access control. Auto-promotes plain entities to AgentEnt Write set_project_scope Set the active project scope for this server session. New entities passed without an explicit projectId may be Write summarize_entity Auto-summarize redundant observations within a single entity. Unlike compress_graph (which merges similar enti Write update_entity \u03B7.5.5.c \u2014 Update an entity with optional optimistic concurrency control. Pass expectedVersion to ass Write update_profile Add a fact to the user profile. Static facts are long-lived (preferences, role, tools). Dynamic facts are rece Write update_saved_search Update a saved search Write upsert_project_context v2.1.0 \u2014 Merge structured project knowledge into the ProjectContextRecord for

READ 140 tools

Read adaptive_retrieve 3B.5 \u2014 Run iterative query-rewriting retrieval. Up to maxRounds of (search \u2192 score coverage \u2192 r Read analyze_cognitive_load Analyze the cognitive load of a set of entities: token density, redundancy ratio, diversity score, and composi Read analyze_query Analyze a search query to extract entities, temporal references, question type, and complexity. Useful for und Read append_project_command v2.1.0 \u2014 Append a documented project command (dedup by name). Read append_project_convention v2.1.0 \u2014 Append one convention to a project context (auto-creates; dedups). Read append_project_fact v2.1.0 \u2014 Append one fact to a project context (auto-creates the record on first call; dedups). Read append_project_glossary_term v2.1.0 \u2014 Append a glossary term (dedup by term). Read audit_history Get the full audit history for a specific entity in chronological order Read audit_query Query the audit log for operations matching filter criteria (operation type, agent ID, entity name, date range Read auto_link_observations Detect entity mentions in observation text and suggest cross-reference relations. Unlike normalize_observation Read boolean_search Perform boolean search with AND, OR, NOT operators Read cache_stats v12.5.0 \u2014 Per-tier snapshot of the global search caches (basic / ranked / boolean / fuzzy) showing hits / Read check_exclusion v2.1.0 \u2014 Check whether content would be blocked by any active forward-blocking rule. Returns {blocked, ru Read check_freshness Calculate the freshness score (0\u20131) for a specific entity based on its TTL and confidence Read check_graph v12.5.0 \u2014 Detect orphan relations (from/to references a missing entity), missing parents (entity.parentId Read compress_context Compress text using n-gram abbreviation with a legend for token-efficient context loading. Unlike format_with_ Read compute_entropy Compute the Shannon entropy of a text string (in bits per character) Read confirm_memory Boost a memory Read counterfactual_query 3B.6 \u2014 Read detect_causal_cycles 3B.6 \u2014 Detect cycles in the causal subgraph rooted at seed. CAVEAT: treats prevents as a directed edge, n Read detect_contradictions Find conflicting observations within an entity using semantic similarity Read detect_heuristic_conflicts v2.1.0 \u2014 Pair-wise overlap/contradiction detection across stored heuristics. Surfaces overlap (same condi Read detect_patterns Detect recurring token-based patterns across observations of a given entity type Read diag v12.5.0 \u2014 Runtime + storage diagnostic snapshot: node version, platform, storage path/type/size, entity + Read diary_read Read recent diary entries for a specialist agent. Returns entries in reverse chronological order. Optionally f Read entity_as_of \u03B7.4.4 \u2014 Time-travel query for an entity. Returns the entity at a given point in time, or null if it Read entity_neighbors v12.5.0 \u2014 Incoming + outgoing relations for one entity, plus in/out degree counts. Lighter than inspect_e Read entity_timeline \u03B7.4.4 \u2014 Get all temporal versions of an entity in chronological order (by validFrom asc, with unboun Read estimate_query_cost Estimate execution cost (time, tokens) for all available search methods on a given query. Unlike analyze_query Read execute_saved_search Execute a previously saved search by name Read extract_facts Extract structured facts from observation text using rule-based extraction Read find_all_paths Find all paths between two entities up to a maximum depth Read find_causes 3B.6 \u2014 Find causal chains ending at the named effect. Searches paths from candidate causes via causal rel Read find_decisions_by_context v2.1.0 \u2014 Substring search across context, decision, and consequences fields. Read find_duplicate_observations v2.1.0 \u2014 Find verbatim duplicate observation strings across distinct entities (SHA-256 exact tier). Compl Read find_duplicates Find potential duplicate entities based on similarity Read find_effects 3B.6 \u2014 Find causal chains starting at the named cause and reaching any candidate effect. Symmetric counte Read find_jaccard_duplicate_observations v2.1.0 \u2014 Find near-duplicate observation strings across distinct entities via token-Jaccard similarity wi Read find_matching_memories_for_rule v2.1.0 \u2014 Dry-run preview: return entities whose observations would match the candidate exclusion pattern. Read find_shortest_path Find the shortest path between two entities in the knowledge graph Read find_similar_entities Find entities similar to a given entity using semantic similarity. Requires embedding provider. Read format_project_context_for_llm v2.1.0 \u2014 Render the ProjectContextRecord as a prose summary suitable for the wakeUp L0 layer or a system Read format_with_salience_budget Format memories for LLM prompt consumption with proportional token allocation based on salience scores Read freshness_report Generate a freshness report across all entities showing fresh, stale, and expired counts Read fuzzy_search Perform fuzzy search with typo tolerance Read get_aliases_for_tag Get all aliases for a canonical tag Read get_ancestors Get all ancestor entities of an entity Read get_artifact Retrieve an artifact entity by its stable ref or entity name Read get_centrality Calculate centrality metrics for entities in the graph Read get_children Get all child entities of an entity Read get_connected_components Find all connected components in the knowledge graph Read get_context_profile Get a ContextWindowManager profile configuration (salience weights, retrieval strategy). Unlike get_profile (u Read get_decayed_memories List memories whose importance has fallen below a threshold due to time-based decay. Unlike get_stale_entities Read get_decision v2.1.0 \u2014 Sync lookup by DecisionId. Read get_decision_chain v2.1.0 \u2014 Walk the supersedes link backward from the supplied id to the original proposal. Returns chain o Read get_descendants Get all descendant entities of an entity Read get_entity_depth Get the depth of an entity in the hierarchy Read get_entity_versions Get the latest version of an entity. If the entity has been superseded by newer versions (via contradiction de Read get_expired_entities Return all entities that have passed their TTL expiry Read get_graph_stats Get statistics about the knowledge graph Read get_heuristic v2.1.0 \u2014 Sync lookup by HeuristicId. Read get_parent Get the parent entity of an entity Read get_procedure 3B.4 \u2014 Load a procedure by id. Read get_procedure_step 3B.4 \u2014 Load a specific step from a procedure by 1-indexed order, OR get the next step relative to current Read get_profile Get the user profile. Returns static facts (long-lived preferences) and dynamic facts (recent session context) Read get_project_context v2.1.0 \u2014 Sync lookup of the ProjectContextRecord for projectId. Read get_project_scope Returns the active project scope for this server session (set via set_project_scope). Returns { projectId } wh Read get_root_entities Get all root entities (entities without parents) Read get_search_suggestions Get search suggestions for a query Read get_stale_entities Return all entities whose freshness score is below a threshold Read get_subtree Get entity and all its descendants as a subgraph Read get_tool_affordance_stats v2.1.0 \u2014 Flat rolling stats for a tool: success_rate, total_calls, common_failure_modes, avg_duration_ms. Read get_version_chain Get all versions of an entity in its version chain. Returns versions sorted by version number ascending. Works Read get_visible_memories Get all memories visible to a specific agent based on visibility rules and trust levels Read get_world_state 3B.7 \u2014 Capture a fresh snapshot of the live graph: entitiesByName + takenAt timestamp + size. Capped at m Read graph_size v12.5.0 \u2014 Graph + storage footprint: entity / relation / observation counts, distinct tag count, avg obse Read health v12.5.0 \u2014 Fast integrity checks: storage:loadGraph, entities:distinct-names, relations:no-orphans, hierar Read heuristic_count v2.1.0 \u2014 Count of stored heuristics. Read hierarchy_tree v12.5.0 \u2014 Hierarchy tree as nested JSON. With an explicit root, returns just that subtree; without, retur Read hybrid_search Search using combined semantic, lexical, and metadata signals. Provides better recall than single-signal searc Read index_embeddings Index all entities for semantic search. Call this after adding entities to enable semantic search. Requires em Read inspect_entity v12.5.0 \u2014 Verbose snapshot of one entity: observations (resolved via ObservationManager so the column-sto Read invalidate_observation \u03B7.4.4 \u2014 Mark a specific observation on an entity as no longer valid. Creates a parallel observationM Read list_artifacts List all artifact entities, with optional filtering by tool name, type, or date Read list_decisions v2.1.0 \u2014 List decisions, optionally filtered by status / sourceSessionId / sourceProjectId. Read list_exclusion_rules v2.1.0 \u2014 Return every registered ExclusionRule. Read list_heuristics v2.1.0 \u2014 All registered heuristics. Read list_projects List all distinct project IDs in the knowledge graph. Returns sorted array of projectId values, excluding glob Read list_refs List all registered refs in the RefIndex, optionally filtered by entity name Read list_role_profiles List all built-in role profiles with their salience weight and context budget configurations Read list_saved_searches List all saved searches Read list_tag_aliases List all tag aliases Read list_tool_affordances v2.1.0 \u2014 All recorded ToolAffordanceRecords. Read match_heuristics v2.1.0 \u2014 Find heuristics whose condition matches input via Jaccard token-overlap \xD7 confidence; sorted Read match_procedure 3B.4 \u2014 Token-overlap match a context description against stored procedures. Returns ranked matches with J Read observations_as_of \u03B7.4.4 \u2014 Get observations valid at a given point in time. Observations with no observationMeta entry Read observe_tool_cancel v2.1.0 \u2014 Drop an in-flight observation without recording (e.g. user cancelled). No-op on unknown callId. Read observe_tool_complete v2.1.0 \u2014 Record successful completion. Computes durationMs from observe_tool_start. No-op on unknown call Read observe_tool_error v2.1.0 \u2014 Record failure with an error message. No-op on unknown callId. Read observe_tool_partial v2.1.0 \u2014 Record a partial result (tool returned a usable but incomplete result). No-op on unknown callId. Read observe_tool_start v2.1.0 \u2014 Begin observing a tool call. Returns a callId the caller threads through observe_tool_complete / Read open_nodes Open specific nodes by their names Read predict_outcome 3B.7 \u2014 Predict downstream effects of an action by walking the causal subgraph. Delegates to CausalReasone Read priority_dedup Smart priority-based deduplication that keeps the highest-scored entity per duplicate group (importance > rece Read propose_decision v2.1.0 \u2014 Propose a new architecture-decision-record (ADR-equivalent). Creates a Read query_as_of Query relations valid at a specific point in time. Returns only relations where validFrom <= date AND (validUn Read query_natural_language Decompose a natural language query into a structured search plan and return matching entities Read rbac_check_permission \u03B7.6.1 \u2014 Check whether an agent can perform an action on a resource type. Falls back to defaultRole=r Read rbac_list_assignments \u03B7.6.1 \u2014 List role assignments for an agent (active or all). Read read_graph Read the entire knowledge graph Read record_heuristic_contradiction v2.1.0 \u2014 Record a counter-example: bumps contradictions; lowers confidence (new = old - old0.2). OCC-prot Read record_tool_outcome v2.1.0 \u2014 Record a single tool-call outcome directly via ToolAffordanceManager (bypasses ToolCallObserver) Read refine_procedure 3B.4 \u2014 Apply caller feedback after a procedure execution. Increments executionCount and updates successRa Read reindex v12.5.0 \u2014 Rebuild search-side indexes that may have drifted (TF-IDF/BM25 ranked + spell-checker vocabular Read reinforce_heuristic v2.1.0 \u2014 Record a successful application: bumps support; raises confidence asymptotically (new = old + (1 Read reinforce_memory Boost a memory Read resolve_ref Resolve a stable alias (ref) to its entity name via the RefIndex Read resolve_tag Resolve a tag to its canonical form Read score_salience Calculate 5-component relevance score for an entity: baseImportance, recencyBoost, frequencyBoost, contextRele Read search_auto Automatically select and execute the best search method based on query characteristics and graph size. Returns Read search_by_date_range Search entities within a date range, with optional filtering by entity type and tags. At least one of startDat Read search_by_time Search entities using a natural language time expression (e.g. Read search_cross_agent Search across agent memories with trust-weighted scoring and visibility filtering Read search_nodes Search for nodes in the knowledge graph based on query string, with optional tag and importance filtering Read search_nodes_ranked Perform TF-IDF ranked search Read semantic_search Search for entities using semantic similarity. Requires embedding provider to be configured via MEMORY_EMBEDDI Read smart_search Intelligent search with automatic query planning and reflection-based refinement. Iteratively improves results Read spell_rebuild_vocabulary v2.1.0 \u2014 Force a rebuild of the SpellChecker vocabulary + n-gram index. Call after bulk entity churn; the Read spell_suggest v2.1.0 \u2014 Suggest close matches for a (potentially misspelled) query over the vocabulary of entity names + Read spell_vocabulary_size v2.1.0 \u2014 Return the count of unique terms in the SpellChecker vocabulary (entity names + tag values by de Read split_transcript Split concatenated multi-session transcripts into per-session chunks via delimiter detection. Preprocessing st Read suggest_tool v2.1.0 \u2014 Suggest tools matching a task hint, ranked by successRate \xD7 recency factor (1.0 at \u22641d, Read supersede_decision v2.1.0 \u2014 Mark an accepted decision as superseded by another. illegal-transition when target is not accept Read synthesize_collaborative_context Synthesize context by traversing the graph neighbourhood from a seed entity and merging high-salience neighbor Read timeline Get chronological relation history for an entity. Returns ALL relations (current and expired) sorted by validF Read tool_observer_in_flight_count v2.1.0 \u2014 Diagnostic: number of in-flight (started but not yet completed) tool-call observations. Read validate_fact_against_world 3B.7 \u2014 Validate a candidate observation against a target entity. Delegates to MemoryValidator.validateCon Read validate_graph Validate the knowledge graph for integrity issues Read visualize_graph Generate a self-contained interactive HTML page with a D3.js force-directed graph visualization. Nodes are col Read wake_up Initialize a 4-layer memory stack context (~600 tokens). L0 loads profile identity, L1 loads top entities by i

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Enhanced Knowledge Graph Memory Server

Can an AI agent delete data through the Enhanced Knowledge Graph Memory Server MCP server? +