get-all-plugin-steps

THE RISK

Low Risk

Why get-all-plugin-steps needs a policy

This tool performs a read-only query of plugin step metadata. It retrieves information about SDK message processing steps for inspection and exploration purposes. No data is modified, deleted, or executed as a result of calling this tool. The operation has no side effects and poses minimal risk if misused by an AI agent — the worst outcome would be exposure of configuration details about existing plugins.

From the tool's definition Tool name is 'get-all-plugin-steps' and description states it 'Get all plugin SDK message processing steps across all assemblies in the environment' — this is a retrieval/query operation that returns metadata about existing plugin configurations without…

Risk signalsBulk/mass operation — affects multiple targets

Documented attack patterns abuse exactly the kind of access get-all-plugin-steps gives an agent:

POLICY

How to control get-all-plugin-steps

PolicyLayer is an MCP gateway — it sits between your AI agents and PowerPlatform MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get-all-plugin-steps:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get-all-plugin-steps": {}
  }
}

get-all-plugin-steps is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register PowerPlatform MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More PowerPlatform MCP tools

Destructive delete-security-role Delete a security role. Destructive — requires confirm: true to proceed. Destructive remove-security-role-privileges Remove privileges from a security role. Loops RemovePrivilegeRole — each privilege is remo Destructive replace-security-role-privileges Replace the entire set of privileges on a role with the supplied list (ReplacePrivilegesRo Execute cancel-flow-run Cancel a running or waiting flow run. Cannot cancel flows already in a terminal state (Suc Execute resubmit-flow-run Resubmit/retry a failed flow run using the original trigger inputs Execute publish-customizations Publish entity customizations or all customizations in Dataverse Write add-security-role-privileges Append privileges to a security role using AddPrivilegesRole. Existing privileges are pres Write add-solution-component Add a component to a Dataverse solution

All 66 PowerPlatform MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get-all-plugin-steps

What does the get-all-plugin-steps tool do? +

Get all plugin SDK message processing steps across all assemblies in the environment. It is categorised as a Read tool in the PowerPlatform MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get-all-plugin-steps? +

Register the PowerPlatform MCP server in PolicyLayer and add a rule for get-all-plugin-steps: 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 PowerPlatform MCP. Nothing to install.

What risk level is get-all-plugin-steps? +

get-all-plugin-steps is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get-all-plugin-steps? +

Yes. Add a rate_limit block to the get-all-plugin-steps 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 get-all-plugin-steps completely? +

Set action: deny in the PolicyLayer policy for get-all-plugin-steps. 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 get-all-plugin-steps? +

get-all-plugin-steps is provided by the PowerPlatform MCP server (michsob/powerplatform-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PowerPlatform MCP tool call.

Start from PowerPlatform MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →