Medium Risk

vault_put

Store a value in the AgentLair Vault. Use this to persist API keys, secrets, or any data your agent needs across sessions. Best practice: encrypt sensitive data client-side before storing (the server stores whatever you send).

Part of the AgentLair server.

vault_put can modify AgentLair data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE AGENTLAIR →

Free to start. No card required.

AI agents use vault_put to create or modify resources in AgentLair. 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 vault_put 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 AgentLair.

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

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

See the full AgentLair policy for all 15 tools.

Get this rule live on your own AgentLair server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY AGENTLAIR →

View all 15 tools →

These attack patterns abuse exactly the kind of access vault_put 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 vault_put only ever does what you allow.

SECURE AGENTLAIR →

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

What does the vault_put tool do? +

Store a value in the AgentLair Vault. Use this to persist API keys, secrets, or any data your agent needs across sessions. Best practice: encrypt sensitive data client-side before storing (the server stores whatever you send).. It is categorised as a Write tool in the AgentLair MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vault_put? +

Register the AgentLair MCP server in PolicyLayer and add a rule for vault_put: 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 AgentLair. Nothing to install.

What risk level is vault_put? +

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

Can I rate-limit vault_put? +

Yes. Add a rate_limit block to the vault_put 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 vault_put completely? +

Set action: deny in the PolicyLayer policy for vault_put. 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 vault_put? +

vault_put is provided by the AgentLair MCP server (@agentlair/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AgentLair tool call.

Deterministic rules across all 15 AgentLair 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.