cleanup_data

// WHEN AI AGENTS USE THIS TOOL

AI agents call cleanup_data to retrieve information from Notebooklm without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

// WHY ENFORCE A POLICY ON CLEANUP_DATA

Even though cleanup_data only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

io-github-pantheon-security-notebooklm-mcp-secure.yaml

tools:
  cleanup_data:
    rules:
      - action: allow

See the full Notebooklm policy for all 31 tools.

// DETAILS

Tool Name cleanup_data

Category Read

MCP Server Notebooklm MCP Server

Risk Level Low

// MORE NOTEBOOKLM TOOLS

Destructive re_auth Destructive remove_notebook Destructive remove_source Destructive reset_session Destructive sync_library Write add_notebook Write add_source Write batch_create_notebooks

View all 31 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like cleanup_data have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Open Library MCP Server get_author_info Open Library MCP Server get_author_photo Open Library MCP Server get_authors_by_name Open Library MCP Server get_book_by_id Open Library MCP Server get_book_by_title Open Library MCP Server get_book_cover

// RELATED READING

// FAQ

What does the cleanup_data tool do? +

ULTRATHINK Deep Cleanup - Scans entire system for ALL NotebookLM MCP data files across 8 categories. Always runs in deep mode, shows categorized preview before deletion. ⚠️ CRITICAL: Close ALL Chrome/Chromium instances BEFORE running this tool! Open browsers can prevent cleanup and cause issues. Categories scanned: 1. Legacy Installation (notebooklm-mcp-nodejs) - Old paths with -nodejs suffix 2. Current Installation (notebooklm-mcp) - Active data, browser profiles, library 3. NPM/NPX Cache - Cached installations from npx 4. Claude CLI MCP Logs - MCP server logs from Claude CLI 5. Temporary Backups - Backup directories in system temp 6. Claude Projects Cache - Project-specific cache (optional) 7. Editor Logs (Cursor/VSCode) - MCP logs from code editors (optional) 8. Trash Files - Deleted notebooklm files in system trash (optional) Works cross-platform (Linux, Windows, macOS). Safe by design: shows detailed preview before deletion, requires explicit confirmation. LIBRARY PRESERVATION: Set preserve_library=true to keep your notebook library.json file while cleaning everything else. RECOMMENDED WORKFLOW for fresh start: 1. Ask user to close ALL Chrome/Chromium instances 2. Run cleanup_data(confirm=false, preserve_library=true) to preview 3. Run cleanup_data(confirm=true, preserve_library=true) to execute 4. Run setup_auth or re_auth for fresh browser session Use cases: Clean reinstall, troubleshooting auth issues, removing all traces before uninstall, cleaning old browser sessions and installation data.. It is categorised as a Read tool in the Notebooklm MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on cleanup_data? +

Add a rule in your Intercept YAML policy under the tools section for cleanup_data. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Notebooklm MCP server.

What risk level is cleanup_data? +

cleanup_data is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit cleanup_data? +

Yes. Add a rate_limit block to the cleanup_data rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block cleanup_data completely? +

Set action: deny in the Intercept policy for cleanup_data. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides cleanup_data? +

cleanup_data is provided by the Notebooklm MCP server (@pan-sec/notebooklm-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Notebooklm