// SCAN REPORT

Nexus Memory

12 tools. 7 can modify or destroy data without limits.

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

Last updated: 30 Jun 2026

7 can modify or destroy data

5 read-only

12 tools total

Community server · catalogue entry verified 30/06/2026

How to control Nexus Memory ↓

TOOL MAP

What Nexus Memory exposes to your agents

Read (5) Write / Execute (5) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Nexus Memory tools

Destructive · High forget This tool performs an irreversible deletion of stored memories. Destructive · Medium unsubscribe Unsubscribing removes a webhook subscription irreversibly — the subscription is deleted and any future webhook deliveries tied to it cease. Execute · High do_update This tool performs a remote code fetch from GitHub and reinstalls software on the host, which constitutes executing external operations with significant blast radius. Write · Medium remember The tool creates and modifies persistent data (memories) in a shared system.

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

POLICY

How to control Nexus Memory

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

Deny destructive operations

{
  "forget": {
    "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

{
  "remember": {
    "limits": [
      {
        "counter": "remember_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "backup": {
    "limits": [
      {
        "counter": "backup_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 Nexus 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 NEXUS MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 12 Nexus Memory tools

DESTRUCTIVE 2 tools

Destructive forget Delete a specific memory by ID. Destructive unsubscribe Remove a webhook subscription by its id (returned from subscribe).

EXECUTE 1 tools

Execute do_update Update Nexus Memory to the latest version. Pulls from GitHub and reinstalls.

WRITE 4 tools

Write remember Store a memory for AI agents. Persists information across sessions. Write restore Restore memories from a backup JSON file. Write update Update an existing memory in-place without losing metadata.

READ 5 tools

Read backup Create a full backup of all memories as JSON file. Read check_update Check if a newer version is available on GitHub. Read health Check if Nexus Memory is running and healthy. Read list_subscriptions List all currently registered webhook subscriptions Read recall Search memories. Returns relevant context from past sessions.

EXPLORE

Related servers

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

FAQ

Questions about Nexus Memory

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

Yes. The Nexus Memory server exposes 2 destructive tools including forget, unsubscribe. 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 Nexus Memory? +

The Nexus Memory server has 4 write tools including remember, restore, subscribe. 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 Nexus Memory.

How many tools does the Nexus Memory MCP server expose? +

12 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Nexus Memory? +

Register the Nexus 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 Nexus Memory tool call.

Deterministic rules across all 12 Nexus Memory tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NEXUS MEMORY →

Instant setup, no code required.

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

// WHERE THIS COMES FROM

These policies come from Nexus Memory's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →