policy-create-or-update
AI agents use policy-create-or-update to create or update resources in Vault MCP Server (mschuchard) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vault MCP Server (mschuchard) environment.
This tool creates or modifies ACL policies, which are reversible write operations. While policies control access and can have significant security implications if misconfigured, the operation itself is not destructive (policies can be updated or deleted later).
From the tool's definition Tool name 'policy-create-or-update' explicitly indicates creation or modification of ACL policies in HashiCorp Vault.
Attacks that exploit this kind of access
policy-create-or-update. It is categorised as a Write tool in the Vault MCP Server (mschuchard) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vault MCP Server (mschuchard) MCP server in PolicyLayer and add a rule for policy-create-or-update: 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 Vault MCP Server (mschuchard). Nothing to install.
policy-create-or-update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the policy-create-or-update 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.
Set action: deny in the PolicyLayer policy for policy-create-or-update. 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.
policy-create-or-update is provided by the Vault MCP Server (mschuchard) MCP server (mschuchard/vault-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →