// SCAN REPORT

Memory

30 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

3 can modify or destroy data

27 read-only

30 tools total

Community server · catalogue entry verified 03/07/2026

How to control Memory ↓

TOOL MAP

What Memory exposes to your agents

Read (27) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Memory tools

Write · Medium save_note This tool creates or modifies notes in a local knowledge store. Write · Medium append_note The name 'append_note' strongly implies creating or modifying a note by appending content to it, which is a reversible write operation. Write · Medium ingest_file 'Ingest' typically means ingesting (importing/indexing) a file into a system, which constitutes a Write operation — creating or modifying stored data (index entries).

3 of Memory's 30 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Memory

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

Rate limit write operations

{
  "append_note": {
    "limits": [
      {
        "counter": "append_note_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "browsing_stats": {
    "limits": [
      {
        "counter": "browsing_stats_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 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 MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 30 Memory tools

WRITE 3 tools

Write append_note append_note Write ingest_file ingest_file Write save_note save_note

READ 27 tools

Read browsing_stats Get overall browsing statistics from all detected browsers. Read commit_details Get details of a specific git commit including changed files. Read detected_browsers List all browsers detected on this system. Read find_connection find_connection Read get_recent_activity get_recent_activity Read git_status Get current git status of a repository. Read graph_search graph_search Read graph_stats Get statistics about the knowledge graph. Read index_stats Get statistics about the vector search index. Read list_conversation_exports List all conversation export files in data/conversations/. Read list_local_files list_local_files Read most_visited_sites Get the most frequently visited websites. Read my_calendars List all Google Calendar calendars accessible to you. Read read_conversations read_conversations Read read_local_file read_local_file Read read_notes read_notes Read recent_browsing_history recent_browsing_history Read recent_commits Get recent git commits from a repository. Read repo_statistics Get statistics about a git repository. Read search_browsing_history Search browsing history by keyword. Read search_calendar search_calendar Read search_in_conversations search_in_conversations Read search_local_files search_local_files Read semantic_search semantic_search Read todays_schedule Get today's calendar schedule. Read upcoming_events Get upcoming Google Calendar events. Read vscode_recent Get recently opened files and folders from VSCode.

FAQ

Questions about Memory

How do I prevent bulk modifications through Memory? +

The Memory server has 3 write tools including append_note, ingest_file, save_note. 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 Memory.

How many tools does the Memory MCP server expose? +

30 tools across 2 categories: Read, Write. 27 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Memory? +

Register the 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 Memory tool call.

Deterministic rules across all 30 Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MEMORY →

Instant setup, no code required.

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