// SCAN REPORT

Mind Mem

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

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

Last updated: 2 Jul 2026

4 can modify or destroy data

12 read-only

16 tools total

Community server · catalogue entry verified 02/07/2026

How to control Mind Mem ↓

TOOL MAP

What Mind Mem exposes to your agents

Read (12) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mind Mem tools

Destructive · High rollback_proposal Rollback operations undo previously applied changes, which can be irreversible in terms of the overwritten or discarded state. Execute · High reindex This tool triggers an external operation (full-text search index and vector index rebuilding) whose effects depend on system state and arguments. Write · Medium approve_apply The name 'approve_apply' indicates the tool likely commits or enacts changes to the Memory OS state—modifying stored memories, governance rules, or system configuration. Write · Medium propose_update The tool creates or modifies memory records within the governed memory layer.

4 of Mind Mem's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mind Mem

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

Deny destructive operations

{
  "rollback_proposal": {
    "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

{
  "approve_apply": {
    "limits": [
      {
        "counter": "approve_apply_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "category_summary": {
    "limits": [
      {
        "counter": "category_summary_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 Mind Mem — 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 MIND MEM →

Instant setup, no code required.

FULL CATALOGUE

All 16 Mind Mem tools

DESTRUCTIVE 1 tools

Destructive rollback_proposal Rollback an applied proposal using its receipt timestamp.

EXECUTE 1 tools

Execute reindex Trigger FTS index rebuild, optionally with vector indexing.

WRITE 2 tools

Write approve_apply approve_apply Write propose_update propose_update

READ 12 tools

Read category_summary category_summary Read find_similar find_similar Read get_mind_kernel get_mind_kernel Read hybrid_search hybrid_search Read index_stats Block counts, index staleness, vector coverage, and MIND kernel status. Read intent_classify intent_classify Read list_contradictions List detected contradictions with resolution analysis. Read list_mind_kernels List available .mind kernel configuration files. Read memory_evolution memory_evolution Read prefetch prefetch Read recall recall Read scan Run integrity scan — contradictions, drift, dead decisions, impact graph.

EXPLORE

Related servers

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

FAQ

Questions about Mind Mem

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

Yes. The Mind Mem server exposes 1 destructive tools including rollback_proposal. 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 Mind Mem? +

The Mind Mem server has 2 write tools including approve_apply, propose_update. 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 Mind Mem.

How many tools does the Mind Mem MCP server expose? +

16 tools across 3 categories: Execute, Read, Write. 12 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Mind Mem? +

Register the Mind Mem 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 Mind Mem tool call.

Deterministic rules across all 16 Mind Mem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MIND MEM →

Instant setup, no code required.

16 Mind Mem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.