// SCAN REPORT

MCP Index Notes

36 tools. 12 can modify or destroy data without limits.

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

Last updated: 4 Jul 2026

12 can modify or destroy data

24 read-only

36 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP Index Notes ↓

TOOL MAP

What MCP Index Notes exposes to your agents

Read (24) Write / Execute (9) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP Index Notes tools

Destructive · High config-reset Resetting configuration to defaults irreversibly overwrites any custom configuration settings the user has made. Destructive · High image-delete Deletion of images is an irreversible operation that permanently removes data. Destructive · High index-delete This tool permanently removes notes from the index without possibility of recovery (unless external backups exist). Write · Medium config-import This tool creates or modifies configuration settings, which is a reversible write operation.

12 of MCP Index Notes's 36 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Index Notes

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

Deny destructive operations

{
  "config-reset": {
    "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

{
  "config-import": {
    "limits": [
      {
        "counter": "config-import_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analysis-auto-tag": {
    "limits": [
      {
        "counter": "analysis-auto-tag_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 MCP Index Notes — 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 MCP INDEX NOTES →

Instant setup, no code required.

FULL CATALOGUE

All 36 MCP Index Notes tools

DESTRUCTIVE 3 tools

Destructive config-reset Reset configuration to default values Destructive image-delete Delete an image by id or all images by key. Destructive index-delete Delete notes by id or by key. Returns count/boolean.

WRITE 9 tools

Write config-import Import configuration from backup or template Write config-update Update server configuration settings Write graph-import-from-notes Import nodes and edges from existing notes: note -> key and note -> tags. Write graph-node-upsert Create or update a graph node with label/type/props. Returns node id. Write image-export Export images (by id or key) to files. Returns file paths. Write image-upsert Store an image (base64 data or file path) under a key. Returns image id. Write index-restore Restore notes from a JSON backup file. Returns imported count. Write index-upsert Create or update a note under a key. Returns the note id. Write streaming-export Stream export of notes and images with format transformation and progress tracking

READ 24 tools

Read analysis-auto-tag Automatically suggest tags for content using NLP analysis Read analysis-cluster-notes Group similar notes into clusters using machine learning Read analysis-content-insights Comprehensive content analysis including sentiment, entities, keywords, and metadata Read analysis-extract-entities Extract entities (emails, URLs, dates, etc.) from note content Read analysis-find-duplicates Find duplicate or very similar notes in the database Read analysis-keyword-extraction Extract key terms and phrases from content using NLP Read analysis-sentiment Analyze sentiment of notes content Read config-export Export current configuration for backup or sharing Read config-get Get current server configuration or specific section Read config-validate Validate configuration schema and values Read graph-neighbors Get neighbors of a node (by id or label/type) up to a depth and limit. Read graph-path Find a path of nodes from A to B (by id or label/type). Read graph-stats Get counts of nodes and edges in the graph store. Read image-get Retrieve images by id or key. Optionally include base64 data. Read index-backup Export all notes to a JSON backup file and return the path. Read index-bootstrap Fetch initial context: list of keys and recent notes per key to seed an LLM conversation. Read index-bootstrap-summary Compact summary of recent notes by key (snippets + top tags) to prepend as system context. Read index-health Health check. Read index-list-keys List known keys and counts. Read index-query Query notes by key or full-text search. Read streaming-search Stream search results in batches for large result sets with filtering and progress tracking Read streaming-similarity Stream similarity analysis between a target note and all other notes Read streaming-tag-analysis Stream comprehensive tag analysis with usage statistics and note associations

EXPLORE

Related servers

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

FAQ

Questions about MCP Index Notes

Can an AI agent delete data through the MCP Index Notes MCP server? +

Yes. The MCP Index Notes server exposes 3 destructive tools including config-reset, image-delete, index-delete. 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 MCP Index Notes? +

The MCP Index Notes server has 9 write tools including config-import, config-update, graph-import-from-notes. 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 MCP Index Notes.

How many tools does the MCP Index Notes MCP server expose? +

36 tools across 3 categories: Destructive, Read, Write. 24 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on MCP Index Notes? +

Register the MCP Index Notes 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 MCP Index Notes tool call.

Deterministic rules across all 36 MCP Index Notes tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP INDEX NOTES →

Instant setup, no code required.

36 MCP Index Notes tools catalogued and risk-classified — across an index of 43,000+ MCP servers.