Total Agent Memory MCP server

Read from the package source without running it. The installed server may list more.

• analogize

  Find past solutions/lessons from OTHER projects whose feature set

• benchmarkwrite action

  Run the eval harness: recall_at_k, prevention_rate, latency percentiles.

• classify_task

  v8.0: classify task into L1-L4 complexity + suggested phases.

• file_context

  BEFORE editing a file, call this to surface past errors, lessons,

• ingest_codebase

  Parse a file or directory into semantic AST chunks

• kg_add_fact

  Record a temporal fact assertion (subject, predicate, object).

• kg_at

  Point-in-time query: return fact assertions valid at `timestamp`

• kg_invalidate_fact

  Close a currently-valid fact assertion. History is retained.

• kg_timeline

  Full chronological history of assertions for a subject.

• learn_error

  Structured error capture: file, error, root_cause, fix, pattern.

• list_intents

  List recent user prompts from the intents table, newest first.

• memory_answer

  Generate and verify a cited answer using the configured reasoning LLM.

• memory_associate

  Associative recall — brain-like spreading activation through knowledge graph.

• memory_concepts

  List or search concepts in the knowledge graph.

• memory_consolidate

  Find and merge duplicate/similar knowledge records. Keeps the longest version,

• memory_consolidate_status

  v11.0 W2-G: report the consolidation daemon state — per-project last-run,

• memory_context_build

  Build optimal context for a query. Combines: spreading activation + knowledge graph

• memory_deletewrite action

  Delete a knowledge record (soft-delete). Removes from search results and ChromaDB.

• memory_entity_resolve

  v11.0 W1-F: resolve a mention to its canonical entity within a project+type.

• memory_episode_recall

  Find past episodes (experiences). Search by concepts, outcome, project, or impact.

• memory_episode_save

  Save an episode — narrative of WHAT HAPPENED and HOW.

• memory_eval_contradictions

  v11.0 Phase 8: runs contradiction_detector against a labelled

• memory_eval_entity_consistency

  v11.0 Phase 8: verifies entity_dedup canonicalization is stable

• memory_eval_locomo

  v11.0 Phase 8: run the LongMemEval-style recall+prevention

• memory_eval_long_context

  v11.0 Phase 8: large-context recall scenario. Saves N records

• memory_eval_recall

  v11.0 Phase 8: generic recall benchmark on a dataset path or a

• memory_eval_temporal

  v11.0 Phase 8: temporal recall using temporal_kg + temporal_filter.

• memory_explain_search

  v11.0: same as memory_search_fast but returns a per-tier breakdown

• memory_export

  Export all knowledge as JSON for backup or migration.

• memory_extract_session

  Get pending session transcripts for knowledge extraction.

• memory_forget

  Apply retention policy: archive stale records (>180d, never recalled, low confidence),

• memory_get

  Batched fetch by ID — complement to memory_recall(mode='index').

• memory_graph

  Query the unified knowledge graph. Returns neighborhood of a node:

• memory_graph_index

  Reindex CLAUDE.md rules and skills into the knowledge graph.

• memory_graph_stats

  Knowledge graph statistics: nodes, edges, communities, top concepts, health metrics.

• memory_history

  View version history for a knowledge record. Shows the chain of superseded versions

• memory_index_passages

  Build local passage indexes before evidence searches. Repeat using next_after_id until remaining=0.

• memory_observe

  Save a lightweight observation (auto-capture). No dedup, no ChromaDB — fast and cheap.

• memory_perf_report

  v11.0: dump in-process telemetry counters (search_total_ms, embed_ms,

• memory_rebuild_embeddings

  v11.0: re-encode every record (or every record in a given embedding

• memory_rebuild_fts

  v11.0: drop and rebuild the SQLite FTS5 virtual table from `knowledge`

• memory_recall

  Search ALL memory: decisions, solutions, facts, lessons from ALL past sessions.

• memory_recall_iterative

  v11.0 W1-B: IRCoT-style iterative retrieval. Decomposes the query into

• memory_reflect_nowwrite action

  Run reflection (the 'sleep' process). Consolidates knowledge, finds patterns,

• memory_relatewrite action

  Create a typed relation between two knowledge records. Enriches graph expansion in Tier 4 search.

• memory_save

  Save knowledge explicitly. Types: decision (MUST include WHY in context),

• memory_save_fast

  v11.0: same as memory_save but routes through the fast hot path

• memory_search_by_tag

  Search knowledge by tag. Returns all active records with matching tag (partial match).

• memory_search_fast

  v11.0: like memory_recall but with rerank=False, diverse=False forced.

• memory_self_assess

  Self-assessment: how competent am I in given domains? Shows level, confidence, blind spots.

• memory_skill_get

  Find skills matching a trigger. Skills are learned procedures — HOW to do things.

• memory_skill_updatewrite action

  Record skill usage or refine a skill. Updates success rate and metrics.

• memory_stats

  Memory statistics with health metrics: sessions, knowledge by type/project,

• memory_temporal_query

  v11.0 W1-C: deterministic temporal reasoning — Allen interval relations,

• memory_timeline

  Browse session history. sessions_ago=N for 'N sessions ago',

• memory_updatewrite action

  Update existing knowledge. Finds old by search query, supersedes it, creates new version.

• memory_warmup

  v11.0: pre-load FastEmbed model and open the vector store, so the

• memory_wiki_generate

  v10 — Render the per-project wiki digest (top decisions,

• phase_transition

  v8.0: advance a task to the next phase.

• rule_set_phase

  Attach or remove a phase scope on a rule (v8.0 lazy rule loading).

• save_decision

  v8.0: save a structured architectural decision (options + criteria matrix +

• save_intent

  Persist one user prompt into the `intents` table (same source as the

• search_intents

  Substring search over user prompts (LIKE). Returns newest match first.

• self_error_log

  Log an error/failure for pattern analysis. Call AUTOMATICALLY when:

• self_insight

  Manage insights from error patterns (ExpeL-style). Actions:

• self_patterns

  Analyze error patterns and self-improvement stats. Views:

• self_reflect

  Save a verbal self-reflection (Reflexion pattern).

• self_rules

  Manage behavioral rules (SOUL). Rules are promoted insights that shape agent behavior.

• self_rules_context

  Get active behavioral rules for current session.

• session_end

  End-of-session capture: summary + highlights + pitfalls + next_steps

• session_init

  At session start: return the most recent unconsumed end-of-session

• task_createwrite action

  v8.0: start a task in `van` phase (auto-classifies level if missing).

• task_phases_list

  v8.0: list all phases of a task in chronological order.

• workflow_learn

  Record a learned workflow (named sequence of steps) for future reuse.

• workflow_predict

  Predict outcome (success probability, avg duration) for a workflow

• workflow_track

  Record a workflow execution outcome. Outcome ∈

• Code scan265 source files scanned20/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 4 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Grade history

• 2026-09-19restoreD → Ascore 85: eval / new Function used

Total Agent Memory: common questions

Is Total Agent Memory MCP server safe?

Yes, by our scan: it is graded A (85/100). Read the Total Agent Memory safety report

How do I install Total Agent Memory?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Total Agent Memory need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Total Agent Memory maintained?

The last commit was 4 days ago (2026-09-15). The latest release is v14.0.0.

What can I use instead of Total Agent Memory?

Servers from other publishers that do the same job: rag-rat MCP server, Inite Brain MCP server and IWE MCP server. Compare all Total Agent Memory alternatives.