patchProject · MCP SSE Ory Server MCP: Risk & Policy

WHAT IT DOES

What patchProject does on MCP SSE Ory Server

AI agents use patchProject to create or update resources in MCP SSE Ory Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP SSE Ory Server environment.

WHY IT NEEDS A POLICY

Why patchProject needs a policy

The 'patch' operation modifies project configuration or settings within an Ory Network workspace in a reversible manner. This is a Write operation rather than Destructive since patches can be reverted or modified further.

From the tool's definition Tool name 'patchProject' and description 'Patch a project by ID' indicate modification of existing project data. Patching is a partial update operation that modifies data reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

patchProject Rate-limited

patchProject 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "patchProject": {
      "limits": [
        {
          "counter": "patchproject_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP SSE Ory Server, so you can run agents against it safely.

FAQ

Questions about patchProject

What does the patchProject tool do? +

Patch a project by ID for a given Ory Network workspace. It is categorised as a Write tool in the MCP SSE Ory Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on patchProject? +

Register the MCP SSE Ory Server MCP server in PolicyLayer and add a rule for patchProject: 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 MCP SSE Ory Server. Nothing to install.

What risk level is patchProject? +

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

Can I rate-limit patchProject? +

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

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

patchProject is provided by the MCP SSE Ory Server MCP server (ory/mcp-sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.