AI agents use patch to create or update resources in Surreal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Surreal environment.
PATCH operations in databases reversibly modify data (Write category) rather than permanently deleting it (Destructive) or executing arbitrary code (Execute). Given the sibling tools are standard CRUD operations and this is a database bridge, 'patch' most likely performs a partial update similar to 'update' or 'merge'. Severity is medium because misuse could modify unintended records, but the operation is reversible.
From the tool's definition Tool name is 'patch' and sibling tools include create, delete, insert, merge, query, relate, select, update, upsert on a SurrealDB MCP server. In database contexts, 'patch' typically performs partial/conditional updates.
Documented attack patterns abuse exactly the kind of access patch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Surreal, and nothing reaches the server without passing your rules. This is the rule we recommend for patch:
{
"version": "1",
"default": "deny",
"tools": {
"patch": {
"limits": [
{
"counter": "patch_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}patch stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
patch. It is categorised as a Write tool in the Surreal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Surreal MCP server in PolicyLayer and add a rule for patch: 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 Surreal. Nothing to install.
patch 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 patch 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 patch. 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.
patch is provided by the Surreal MCP server (lfnovo/surreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Surreal, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Surreal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.