# memory_update

A write tool on the Agent-Memory-OS MCP server.

Agent View of the PolicyLayer registry record for `memory_update`. HTML page: https://policylayer.com/tools/agent-memory-os/memory-update

## Facts

- Tool: `memory_update`
- Server: Agent-Memory-OS (`yamantaka520/Agent-Memory-OS`) — https://policylayer.com/tools/agent-memory-os.md
- Homepage: https://github.com/yamantaka520/Agent-Memory-OS
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "memory_update",
    "arguments": {}
  }
}
```

## Why memory_update is rated Medium

The 'memory_update' tool modifies existing memory entries in the SQLite-backed memory store. This is a Write operation because it changes data reversibly without deletion or execution of arbitrary code. Severity is medium because misuse could corrupt agent memory state or overwrite important context, but the scope is limited to memory records rather than system-wide or financial impacts.

From the tool's own definition: "Tool name 'memory_update' indicates modification of stored data. Sibling tools include 'memory_add' (clearly Write), 'memory_search' (Read), and 'memory_recall_feedback' (Write)."

## Use case

AI agents use memory_update to create or update resources in Agent-Memory-OS, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent-Memory-OS environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Agent-Memory-OS:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_update": {
      "limits": [
        {
          "counter": "memory_update_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Agent-Memory-OS (11)

- `memory_offload_context` — Other — https://policylayer.com/tools/agent-memory-os/memory-offload-context.md
- `memory_search` — Read — https://policylayer.com/tools/agent-memory-os/memory-search.md
- `memory_snapshot_diff` — Read — https://policylayer.com/tools/agent-memory-os/memory-snapshot-diff.md
- `memory_add` — Write — https://policylayer.com/tools/agent-memory-os/memory-add.md
- `memory_consolidate` — Write — https://policylayer.com/tools/agent-memory-os/memory-consolidate.md
- `memory_context_pack` — Write — https://policylayer.com/tools/agent-memory-os/memory-context-pack.md
- `memory_link` — Write — https://policylayer.com/tools/agent-memory-os/memory-link.md
- `memory_orchestrate_context` — Write — https://policylayer.com/tools/agent-memory-os/memory-orchestrate-context.md
- `memory_recall_feedback` — Write — https://policylayer.com/tools/agent-memory-os/memory-recall-feedback.md
- `memory_reload_context` — Write — https://policylayer.com/tools/agent-memory-os/memory-reload-context.md
- `memory_share` — Write — https://policylayer.com/tools/agent-memory-os/memory-share.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agent-memory-os · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/agent-memory-os