Medium Risk

write_memory

Write a new memory entry to your hierarchical long-term memory (.hmem).

Part of the hmem — Humanlike Memory for AI Agents server.

write_memory can modify hmem — Humanlike Memory for AI Agents data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE HMEM — HUMANLIKE MEMORY FOR AI AGENTS →

Free to start. No card required.

AI agents use write_memory to create or modify resources in hmem — Humanlike Memory for AI Agents. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call write_memory repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach hmem — Humanlike Memory for AI Agents.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "write_memory": {
      "limits": [
        {
          "counter": "write_memory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full hmem — Humanlike Memory for AI Agents policy for all 23 tools.

Get this rule live on your own hmem — Humanlike Memory for AI Agents server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY HMEM — HUMANLIKE MEMORY FOR AI AGENTS →

View all 23 tools →

These attack patterns abuse exactly the kind of access write_memory gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so write_memory only ever does what you allow.

SECURE HMEM — HUMANLIKE MEMORY FOR AI AGENTS →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the write_memory tool do? +

Write a new memory entry to your hierarchical long-term memory (.hmem).. It is categorised as a Write tool in the hmem — Humanlike Memory for AI Agents MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on write_memory? +

Register the hmem — Humanlike Memory for AI Agents MCP server in PolicyLayer and add a rule for write_memory: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches hmem — Humanlike Memory for AI Agents. Nothing to install.

What risk level is write_memory? +

write_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit write_memory? +

Yes. Add a rate_limit block to the write_memory rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block write_memory completely? +

Set action: deny in the PolicyLayer policy for write_memory. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides write_memory? +

write_memory is provided by the hmem — Humanlike Memory for AI Agents MCP server (hmem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every hmem — Humanlike Memory for AI Agents tool call.

Deterministic rules across all 23 hmem — Humanlike Memory for AI Agents tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.