// SCAN REPORT

Mentedb

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

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

Last updated: 5 Jul 2026

3 can modify or destroy data

1 read-only

4 tools total

Verified server · catalogue entry verified 05/07/2026 · full schemas captured for 4 of 4 tools

How to control Mentedb ↓

TOOL MAP

What Mentedb exposes to your agents

Read (1) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Mentedb costs in tokens

788 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

260 heaviest tool: process_turn

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mentedb tools

Destructive · High forget_memory This tool permanently removes memory records from the MenteDB persistent storage without the ability to recover them. Write · Medium process_turn The tool writes/stores new memory data on every conversation turn, which is a persistent write operation. Write · Low store_memory The tool creates or modifies data (storing facts, preferences, decisions, corrections) in a reversible manner.

3 of Mentedb's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mentedb

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

Deny destructive operations

{
  "forget_memory": {
    "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

{
  "process_turn": {
    "limits": [
      {
        "counter": "process_turn_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "search_memories": {
    "limits": [
      {
        "counter": "search_memories_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 Mentedb — 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 MENTEDB →

Instant setup, no code required.

FULL CATALOGUE

All 4 Mentedb tools

DESTRUCTIVE 1 tools

Destructive forget_memory Delete a memory by ID. Use when the user asks to forget something.

WRITE 2 tools

Write process_turn Process a conversation turn. Stores new memories and returns relevant context from past conversations. MUST be Write store_memory Store an important fact, preference, decision, or correction. Use types: semantic (facts), procedural (how-to)

READ 1 tools

Read search_memories Search memories by semantic similarity, or get full content of a specific memory by UUID. Use when you need to

EXPLORE

Related servers

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

FAQ

Questions about Mentedb

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

Yes. The Mentedb server exposes 1 destructive tools including forget_memory. 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 Mentedb? +

The Mentedb server has 2 write tools including process_turn, store_memory. 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 Mentedb.

How many tools does the Mentedb MCP server expose? +

4 tools across 4 categories: Destructive, Other, Read, Write. 1 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Mentedb? +

Register the Mentedb 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 Mentedb tool call.

Deterministic rules across all 4 Mentedb tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MENTEDB →

Instant setup, no code required.

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