// SCAN REPORT

Junto Memory

64 tools. 19 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

19 can modify or destroy data

45 read-only

64 tools total

Community server · catalogue entry verified 29/06/2026

How to control Junto Memory ↓

TOOL MAP

What Junto Memory exposes to your agents

Read (45) Write / Execute (18) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Junto Memory tools

Destructive · High memory_cancel_reminder Cancel a pending reminder. Caller must own the reminder. Execute · Medium memory_start_session memory_start_session Write · Medium memory_add_backlog_item memory_add_backlog_item Write · Medium memory_archive_by_tag memory_archive_by_tag

19 of Junto Memory's 64 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Junto Memory

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

Deny destructive operations

{
  "memory_cancel_reminder": {
    "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

{
  "memory_add_backlog_item": {
    "limits": [
      {
        "counter": "memory_add_backlog_item_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "memory_ack_directive": {
    "limits": [
      {
        "counter": "memory_ack_directive_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 Junto Memory — 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 JUNTO MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 64 Junto Memory tools

DESTRUCTIVE 1 tools

Destructive memory_cancel_reminder Cancel a pending reminder. Caller must own the reminder.

EXECUTE 1 tools

Execute memory_start_session memory_start_session

WRITE 17 tools

Write memory_add_backlog_item memory_add_backlog_item Write memory_archive_by_tag memory_archive_by_tag Write memory_complete_backlog_item Mark a backlog item as completed or won't do. Write memory_export_skills memory_export_skills Write memory_lock_files memory_lock_files Write memory_pin_skill memory_pin_skill Write memory_register_function memory_register_function Write memory_register_skill memory_register_skill Write memory_restore_by_tag memory_restore_by_tag Write memory_send_message memory_send_message Write memory_set_autopilot memory_set_autopilot Write memory_set_reminder memory_set_reminder Write memory_sync_push memory_sync_push Write memory_unlock_files memory_unlock_files Write memory_update_backlog_item memory_update_backlog_item Write memory_update_message_status memory_update_message_status Write memory_update_work memory_update_work

READ 45 tools

Read memory_ack_directive memory_ack_directive Read memory_acknowledge_message Acknowledge receipt of a message (shortcut for status=received). Read memory_admin memory_admin Read memory_autopilot_check_budget memory_autopilot_check_budget Read memory_autopilot_count memory_autopilot_count Read memory_autopilot_digest memory_autopilot_digest Read memory_autopilot_status memory_autopilot_status Read memory_batch_backlog memory_batch_backlog Read memory_become_librarian memory_become_librarian Read memory_change_status memory_change_status Read memory_checklist memory_checklist Read memory_claim_message memory_claim_message Read memory_confirm_skill memory_confirm_skill Read memory_db memory_db Read memory_define_spec memory_define_spec Read memory_end_session memory_end_session Read memory_enrich_function memory_enrich_function Read memory_find_function memory_find_function Read memory_get_active_work memory_get_active_work Read memory_get_agent_status Get status of Claude agents. Read memory_get_by_id memory_get_by_id Read memory_get_emission_stats memory_get_emission_stats Read memory_get_enrichment_queue Get pending function references awaiting librarian enrichment. Read memory_get_locks memory_get_locks Read memory_get_messages memory_get_messages Read memory_get_skill Fetch one skill (full body) by id (skill_) or by name. Read memory_get_spec Get a spec by name, optionally at a specific version. Read memory_guidelines memory_guidelines Read memory_health memory_health Read memory_heartbeat memory_heartbeat Read memory_list_agents memory_list_agents Read memory_list_alerts memory_list_alerts Read memory_list_backlog memory_list_backlog Read memory_list_projects List all projects with memory collections. Read memory_list_reminders List your reminders. Read memory_list_skills memory_list_skills Read memory_list_specs memory_list_specs Read memory_pause_autopilot memory_pause_autopilot Read memory_project memory_project Read memory_query memory_query Read memory_record_learning memory_record_learning Read memory_search_global memory_search_global Read memory_standup memory_standup Read memory_store memory_store Read memory_sync_pull memory_sync_pull

EXPLORE

Related servers

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

FAQ

Questions about Junto Memory

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

Yes. The Junto Memory server exposes 1 destructive tools including memory_cancel_reminder. 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 Junto Memory? +

The Junto Memory server has 17 write tools including memory_add_backlog_item, memory_archive_by_tag, memory_complete_backlog_item. 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 Junto Memory.

How many tools does the Junto Memory MCP server expose? +

64 tools across 4 categories: Destructive, Execute, Read, Write. 45 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on Junto Memory? +

Register the Junto 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 Junto Memory tool call.

Deterministic rules across all 64 Junto Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON JUNTO MEMORY →

Instant setup, no code required.

64 Junto Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.