New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
// SCAN REPORT

Mapi Agent Memory

252 tools. 108 can modify or destroy data without limits.

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

Last updated:

108 can modify or destroy data
144 read-only
252 tools total

Community server · catalogue entry checked 30/07/2026

How to control Mapi Agent Memory ↓

TOOL MAP

What Mapi Agent Memory exposes to your agents

Read (144) Write / Execute (104) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Mapi Agent Memory tools

Destructive · Critical delete_path The name 'delete_path' strongly suggests deletion of files or data paths without reversibility. Destructive · High rollback_memory_pointer_lifecycle_remediation_execution A rollback operation reverts or undoes previously applied remediation changes. Destructive · High expire_memory_capture_item Expiring a durable capture review item permanently removes it from the active review pipeline without producing any compensating artifact (memory). Destructive · High gemma_worker_cancel_job gemma_worker_cancel_job

108 of Mapi Agent Memory's 252 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mapi Agent Memory

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

Deny destructive operations
{
  "delete_path": {
    "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
{
  "add_review_note": {
    "limits": [
      {
        "counter": "add_review_note_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "bootstrap_agent_context": {
    "limits": [
      {
        "counter": "bootstrap_agent_context_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Mapi Agent Memory — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON MAPI AGENT MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 252 Mapi Agent Memory tools

DESTRUCTIVE 4 tools
Destructive delete_path delete_path Destructive expire_memory_capture_item Expire a durable capture review item without creating a memory. Destructive gemma_worker_cancel_job gemma_worker_cancel_job Destructive rollback_memory_pointer_lifecycle_remediation_execution Execute an exact guarded rollback of a pointer-lifecycle remediation run.
EXECUTE 28 tools
Execute apply_escalation_reactions apply_escalation_reactions Execute apply_memory_lifecycle_remediation Execute the guarded legacy lineage remediation after explicit confirmation. Execute apply_memory_pointer_lifecycle_remediation_execution Execute an explicitly approved frozen pointer-lifecycle remediation manifest. Execute backfill_semantic_embeddings Generuje embeddingi dla wspomnień które jeszcze ich nie mają. Execute gemma_lms_load Load configured Gemma model through the LM Studio CLI. Execute gemma_lms_unload Unload configured Gemma model through the LM Studio CLI. Execute gemma_worker_run_job gemma_worker_run_job Execute gemma_worker_run_task gemma_worker_run_task Execute git_push Push the current branch or an explicit branch. Execute git_status Run git status --short. Execute preview_memory_pointer_lifecycle_remediation_execution_rollback Preview exact snapshot-based rollback of a pointer-lifecycle remediation run. Execute preview_undo_run preview_undo_run Execute query_sql query_sql Execute rollback_memory_hygiene_run rollback_memory_hygiene_run Execute rollback_memory_lifecycle_remediation Execute guarded snapshot-based rollback for a legacy remediation run. Execute rollback_memory_supersession_run Execute guarded rollback for a Memory v3 supersession apply run. Execute run_conflicts_v1 run_conflicts_v1 Execute run_consolidation_v1 run_consolidation_v1 Execute run_escalation_check run_escalation_check Execute run_powershell Run a PowerShell script from the dev MCP server. Execute run_pytest Run pytest from the repository root. Execute run_sandman_ai Sandman AI (wykonanie) — używa LM Studio (Qwen) do oceny wspomnień i wprowadza zmiany. Execute run_sandman_gemma_hygiene Run Gemma-style Sandman hygiene for low-risk validated actions only. Semantic archive stays review-only. Execute run_sandman_quality_hygiene Run deterministic Sandman quality hygiene repairs with audit events. Execute run_sandman_v1 Sandman V1 — archiwizacja, downgrade, duplikaty. Execute run_workshop_action Run an action from a workshop through the compact MCP surface. Execute sandman_memory_chat Sandman Memory Chat — host steruje narzędziami MAPI dla lokalnego modelu. Execute undo_run undo_run
WRITE 76 tools
Write add_review_note add_review_note Write add_validation_event add_validation_event Write append_file_text append_file_text Write apply_approved_memory_consolidation_proposal Apply an approved merge_duplicates proposal as a rollback-safe consolidation run. Write apply_conflict_resolution apply_conflict_resolution Write apply_memory_capture_reconciliation Atomically apply one approved Memory v3 capture reconciliation preview. Write apply_memory_hygiene apply_memory_hygiene Write apply_memory_retention_batch Atomically apply 1..10 approved items after a trusted internal online backup. Write apply_memory_retention_review Atomically apply one approved and fresh retention review item. Write apply_memory_supersession Execute guarded Memory v3 supersession apply. Write approve_memory approve_memory Write approve_memory_consolidation_proposal Approve a consolidation proposal by changing review-state only. Write approve_scope_promotion Zatwierdza wniosek o promocję scope i natychmiast zmienia visibility_scope wspomnienia. Write archive_conversation archive_conversation Write archive_ingest_item Archives a research ingest item in quarantine. Write archive_memory_v2 archive_memory_v2 Write bulk_repair_owner_mappings bulk_repair_owner_mappings Write bulk_set_duplicate_candidate_sla bulk_set_duplicate_candidate_sla Write bulk_set_memory_owner bulk_set_memory_owner Write bulk_set_memory_sla bulk_set_memory_sla Write confirm_memory_v2 confirm_memory_v2 Write create_ingest_item Creates a quarantined research ingest item. Does not create normal memory. Write create_memory Legacy compatibility alias. May still route through capture reconciliation. Write create_memory_draft create_memory_draft Write create_memory_from_proposal Approve a memory proposal and persist it as a normal memory entry. Write create_memory_version create_memory_version Write create_private_memory Tworzy prywatne wspomnienie przypisane do konkretnego użytkownika. Write create_project_memory Tworzy wspomnienie projektowe widoczne dla wszystkich członków workspace w danym projekcie. Write create_workspace_memory Tworzy wspomnienie workspace-level widoczne dla wszystkich członków workspace. Write decide_memory_retention_review Approve or reject one pending retention review item. Write demote_memory Degraduje wspomnienie do niższej warstwy. Write gemma_worker_approve_job gemma_worker_approve_job Write gemma_worker_create_job gemma_worker_create_job Write gemma_worker_prepare_plan gemma_worker_prepare_plan Write gemma_worker_reject_job gemma_worker_reject_job Write git_commit Create a git commit. Optionally stages all changes first. Write insert_after_marker Safely insert text after an exact marker in a text file. Write insert_before_marker Safely insert text before an exact marker in a text file. Write link_memories link_memories Write make_dir make_dir Write mark_memory_stale mark_memory_stale Write move_path move_path Write normalize_project_scope Normalize one active project memory from global/default scope to project scope and record an audit event. Write preview_memory_capture_reconciliation Build and persist a deterministic capture reconciliation preview without applying it. Write promote_ingest_item Promotes a quarantined ingest item into one concise normal memory. Write promote_memory Awansuje wspomnienie na wyższą warstwę. Write propose_memory Queue an uncertain or agent-generated memory proposal for review. Write propose_scope_promotion Zgłasza wniosek o poszerzenie scope wspomnienia (np. private → project, project → workspace) Write record_conflict_decision Records an operator's manual decision for a conflict pair. Write reject_ingest_item Rejects a research ingest item without touching normal memory. Write reject_memory reject_memory Write reject_memory_consolidation_proposal Reject a consolidation proposal by changing review-state only. Write reject_scope_promotion Odrzuca wniosek o promocję scope. Nie zmienia visibility_scope wspomnienia. Write repair_owner_mapping_issue repair_owner_mapping_issue Write replace_once Safely replace one exact text occurrence in a text file. Write return_memory_to_review return_memory_to_review Write review_memory_capture_item Approve or reject a durable capture review item without creating a memory. Write rollback_memory_consolidation_apply_run Execute guarded rollback for a consolidation apply run via the existing undo mechanism. Write rollout_owner_catalog_to_project rollout_owner_catalog_to_project Write run_memory_linking_pass Deterministycznie tworzy brakujace linki grafu pamieci. Write save_memory Persist an explicit or deliberately autonomous private-MAPI memory. Write save_memory_capture_proposal Persist a durable capture review item without creating a memory. Write save_memory_retention_review Persist an idempotent pending retention review item from a fresh preview. Write set_duplicate_candidate_sla set_duplicate_candidate_sla Write set_feature_flag set_feature_flag Write set_memory_owner set_memory_owner Write set_memory_priority set_memory_priority Write set_memory_sla set_memory_sla Write set_owner_target_active set_owner_target_active Write upsert_feature_flag upsert_feature_flag Write upsert_owner_directory_item upsert_owner_directory_item Write upsert_owner_role_mapping upsert_owner_role_mapping Write upsert_project_key_alias Create or update one project_key alias for explicit alias-mode retrieval. Write upsert_sla_policy upsert_sla_policy Write write_file_base64 write_file_base64 Write write_file_text write_file_text
READ 144 tools
Read bootstrap_agent_context Restore MAPI's core identity and current continuity anchors. Read check_gemma_runtime Pelna diagnostyka Gemma runtime: serwer, model, test chat completion. Read check_sandman_gemma_lms_status Report LM Studio/LMS residency diagnostics for Sandman Gemma without loading or unloading models. Read compare_memory_modes Compare classic retrieval output with v2 restore/project-card output on the same scenario. Read deprecate_memory deprecate_memory Read evaluate_feature_flag evaluate_feature_flag Read explain_conflict explain_conflict Read find_memories find_memories Read gemma_ask Ask Gemma a read-only question through LM Studio. Read gemma_coding_task Ask Gemma for structured read-only coding advice. Read gemma_lms_status Return LM Studio/LMS diagnostics for the MAPI Gemma coding agent. Read gemma_worker_get_job gemma_worker_get_job Read gemma_worker_get_report gemma_worker_get_report Read gemma_worker_prepare_task gemma_worker_prepare_task Read gemma_worker_report gemma_worker_report Read gemma_worker_status gemma_worker_status Read get_conflict_clusters get_conflict_clusters Read get_conflict_history get_conflict_history Read get_conflict_pairs get_conflict_pairs Read get_conflict_quality_metrics Returns quality metrics for the conflict explainer subsystem. Read get_conflict_reasoning get_conflict_reasoning Read get_conflict_registry Return a registry-style view of conflict clusters with lifecycle status. Read get_conflict_report get_conflict_report Read get_conflict_system_status Returns operational status of the conflict explainer subsystem. Read get_conversation Zwraca pełny transkrypt rozmowy po conversation_id. Read get_db_info get_db_info Read get_effective_owner_workload get_effective_owner_workload Read get_escalation_dashboard Dashboard eskalacji: podsumowanie pending escalations, najczęstsze przyczyny, avg czas reakcji. Read get_escalation_history Zwraca historię eskalacji z opcjonalnym filtrowaniem. Read get_feature_flag get_feature_flag Read get_ingest_item Returns a single quarantined research ingest item. Read get_layer_stats Zwraca statystyki rozkładu wspomnień według layer_code, area_code i state_code. Read get_memory get_memory Read get_memory_capture_review_item Get one durable capture review item. Read get_memory_consolidation_apply_run Return one read-only audit record for a consolidation apply run. Read get_memory_consolidation_lifecycle_report Return a read-only lifecycle report for consolidation proposals and their apply/rollback audit chain. Read get_memory_consolidation_proposal Return one consolidation proposal with linked source memory previews. Read get_memory_consolidation_snapshot_integrity_report Report whether stored consolidation apply and rollback preview snapshots are complete and auditable. Read get_memory_current_state get_memory_current_state Read get_memory_forgetting_review Return operator-focused review buckets for stale/archive/superseded hygiene. Read get_memory_health_report Return a read-only health report for memory v2 operator review. Read get_memory_hygiene_inventory get_memory_hygiene_inventory Read get_memory_hygiene_run get_memory_hygiene_run Read get_memory_lifecycle_remediation_inventory Inventory the allowlisted legacy lineage remediation plan without writes. Read get_memory_lifecycle_remediation_run Inspect one legacy lifecycle remediation run without writes. Read get_memory_links get_memory_links Read get_memory_pointer_lifecycle_remediation_execution_run Inspect one pointer-lifecycle remediation run without writes. Read get_memory_pointer_lifecycle_remediation_inventory Inventory global pointer-only lifecycle lineages without writes. Read get_memory_provenance get_memory_provenance Read get_memory_retention_review Get one durable retention review item. Read get_memory_supersession_run Get one read-only Memory v3 supersession apply run. Read get_operational_queue_dashboard get_operational_queue_dashboard Read get_owner_catalog_governance_checklist Zwraca listę kontrolną (checklist) dla operacji na katalogu właścicieli. Read get_owner_catalog_governance_history get_owner_catalog_governance_history Read get_owner_catalog_health get_owner_catalog_health Read get_owner_catalog_repair_summary get_owner_catalog_repair_summary Read get_owner_governance_history get_owner_governance_history Read get_owner_mapping_batch_candidates get_owner_mapping_batch_candidates Read get_owner_mapping_repair_audit get_owner_mapping_repair_audit Read get_owner_rebalance_candidates get_owner_rebalance_candidates Read get_owner_rollout_summary get_owner_rollout_summary Read get_problematic_owner_mappings get_problematic_owner_mappings Read get_promotion_candidates Zwraca listę wspomnień, które spełniają kryteria awansu (evidence_count, importance_score, Read get_quality_alerts get_quality_alerts Read get_queue_observability_metrics get_queue_observability_metrics Read get_root get_root Read get_sandman_gemma_shadow_report Return recent Sandman Gemma preview/shadow runs and agreement metrics. Read-only. Read get_semantic_embedding_stats Zwraca statystyki pokrycia embeddingów — ile wspomnień ma embeddingi, ile nie. Read get_sla_policy_observability get_sla_policy_observability Read get_sleep_run get_sleep_run Read get_sleep_run_actions get_sleep_run_actions Read get_source_quality get_source_quality Read get_version_lineage Zwraca pełne drzewo wersji wspomnienia (przodkowie i potomkowie przez supersedes_memory_id). Read get_workspace_info get_workspace_info Read list_conflicted_memories list_conflicted_memories Read list_conversations Listuje zarchiwizowane rozmowy, opcjonalnie filtrując po project_key / workspace_key / user_key. Read list_dir list_dir Read list_duplicate_candidates_admin list_duplicate_candidates_admin Read list_expired_memories list_expired_memories Read list_feature_flags list_feature_flags Read list_ingest_queue Lists quarantined research ingest items. Read list_memories list_memories Read list_memories_for_user list_memories_for_user Read list_memory_audit list_memory_audit Read list_memory_capture_review_items List durable capture review items. Read list_memory_consolidation_apply_runs List read-only audit records for consolidation apply runs. Read list_memory_consolidation_proposals List consolidation proposals stored as proposal memories with durable review-state. Read list_memory_retention_reviews List durable retention review items. Read list_memory_supersession_runs List read-only Memory v3 supersession apply runs. Read list_memory_versions list_memory_versions Read list_overdue_duplicate_queue list_overdue_duplicate_queue Read list_overdue_expired_queue list_overdue_expired_queue Read list_overdue_revalidation_queue list_overdue_revalidation_queue Read list_overdue_review_queue list_overdue_review_queue Read list_owner_directory_items list_owner_directory_items Read list_owner_role_mappings list_owner_role_mappings Read list_project_key_aliases List configured project_key aliases. Aliases are only used when project_key_mode='aliases'. Read list_project_scope_mismatches List active project memories that still have global or omitted scope without an explicit exception tag. Read list_revalidation_queue list_revalidation_queue Read list_review_events list_review_events Read list_review_queue list_review_queue Read list_scope_promotion_proposals Wyświetla wnioski o promocję scope. Read list_sla_policies list_sla_policies Read list_sleep_runs list_sleep_runs Read list_validation_events list_validation_events Read open_workshop Open a compact workshop index for one operational area. Read preview_apply_memory_consolidation_proposal Preview a rollback-safe apply plan for an approved consolidation proposal. Read preview_bulk_repair_owner_mappings preview_bulk_repair_owner_mappings Read preview_conflict_resolution preview_conflict_resolution Read preview_conflicts_v1 preview_conflicts_v1 Read preview_consolidation_v1 preview_consolidation_v1 Read preview_memory_consolidation_apply_rollback Preview guarded rollback for one consolidation apply run without mutating data. Read preview_memory_hygiene preview_memory_hygiene Read preview_memory_hygiene_rollback preview_memory_hygiene_rollback Read preview_memory_lifecycle_remediation Preview the allowlisted legacy lineage remediation plan without writes. Read preview_memory_lifecycle_remediation_rollback Preview snapshot-based rollback for a legacy remediation run. Read preview_memory_linking_pass Preview kandydatow do deterministycznego linkowania grafu pamieci. Read preview_memory_pointer_lifecycle_remediation Preview guarded pointer-only lifecycle canonicalization without writes. Read preview_memory_pointer_lifecycle_remediation_execution Build or revalidate a frozen pointer-lifecycle execution design without writes. Read preview_memory_quality_gate preview_memory_quality_gate Read preview_memory_retention_policy Build a deterministic redacted retention preview for one memory. Read preview_memory_retention_rollback Preview an exact rollback for an applied archive or expire action. Read preview_memory_supersession Preview guarded Memory v3 supersession without mutating data. Read preview_memory_supersession_rollback Preview guarded rollback for a Memory v3 supersession apply run. Read preview_project_memory_retention Build a deterministic read-only retention preview for one project namespace. Read preview_research_ingest_review Heuristic Sandman-style preview for research ingest quarantine review. Read preview_sandman_ai Sandman AI (preview) — używa LM Studio (Qwen) do oceny wspomnień. Read preview_sandman_gemma_candidates Collect candidate memories for Gemma-based Sandman review. Does not call a model and does not write. Read preview_sandman_gemma_hygiene Preview Gemma-style Sandman hygiene review through parser and host validator. No memory writes, but records an Read preview_sandman_quality_hygiene Preview deterministic Sandman quality hygiene repairs: owner gaps and project scope mismatches. Read preview_sandman_v1 Sandman V1 (preview) — podgląd kandydatów do archiwizacji i downgrade. Read propose_memory_capture Preview a structured memory proposal without writing it to the database. Read read_file_base64 read_file_base64 Read read_file_text read_file_text Read recall_memory recall_memory Read rollback_memory_retention_review Atomically restore the exact pre-apply lifecycle snapshot. Read search_semantic search_semantic Read search_text search_text Read search_verbatim Wyszukuje dokładne dopasowania tekstu (verbatim, FTS5) w wspomnieniach i/lub archiwum rozmów. Read stat_path stat_path Read supersede_memory_v2 supersede_memory_v2 Read validate_migration_0010 validate_migration_0010 Read validate_new_owner_target Waliduje dane nowego targetu właściciela przed dodaniem do katalogu. Read validate_project_override validate_project_override
EXPLORE

Related servers

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

UnClick 1662 tools
adminautomation
Delx Protocol — Agent Recovery & Continuity 1076 tools
adminautomation
Delx Mcp A2a 1068 tools
adminautomation
Nodebench 824 tools
adminautomation
MCP Framework Personal 811 tools
adminautomation
Delx MCP Server 740 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Eda Agent 726 tools
adminautomation
FAQ

Questions about Mapi Agent Memory

Can an AI agent delete data through the Mapi Agent Memory MCP server? +

Yes. The Mapi Agent Memory server exposes 4 destructive tools including delete_path, expire_memory_capture_item, gemma_worker_cancel_job. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mapi Agent Memory? +

The Mapi Agent Memory server has 76 write tools including add_review_note, add_validation_event, append_file_text. 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 Mapi Agent Memory.

How many tools does the Mapi Agent Memory MCP server expose? +

252 tools across 4 categories: Destructive, Execute, Read, Write. 144 are read-only. 108 can modify, create, or delete data.

How do I enforce a policy on Mapi Agent Memory? +

Register the Mapi Agent Memory 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.

Enforce policy on every Mapi Agent Memory tool call.

Deterministic rules across all 252 Mapi Agent Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MAPI AGENT MEMORY →

Instant setup, no code required.

252 Mapi Agent Memory tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Mapi Agent Memory's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.