AI agents use update_shared_step to create or update resources in QASE MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QASE MCP Server environment.
This tool creates or modifies data reversibly by updating a shared step, which is a core Write operation. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), or move money (would be Financial). The blast radius is medium because incorrect updates could affect multiple test cases that reference this shared step, but the operation is reversible through subsequent updates.
From the tool's definition Tool is named 'update_shared_step' and described as 'Update an existing shared step', indicating it modifies an existing resource in the Qase test management platform.
Documented attack patterns abuse exactly the kind of access update_shared_step gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and QASE MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update_shared_step:
{
"version": "1",
"default": "deny",
"tools": {
"update_shared_step": {
"limits": [
{
"counter": "update_shared_step_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_shared_step 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.
Update an existing shared step. It is categorised as a Write tool in the QASE MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QASE MCP Server MCP server in PolicyLayer and add a rule for update_shared_step: 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 QASE MCP Server. Nothing to install.
update_shared_step 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 update_shared_step 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 update_shared_step. 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.
update_shared_step is provided by the QASE MCP Server MCP server (rikuson/mcp-qase). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from QASE MCP Server, 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.
26 QASE MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.