incidents.get

Get a StillOnline incident by ID. Despite the historical name, this returns one incident record for follow-up status updates or review.

Server Stillonline shenwell/stillonline-mcp
Category Read
Risk class Low
Parameters 00 required

What incidents.get does on Stillonline

AI agents call incidents.get to retrieve information from Stillonline without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why incidents.get needs a policy

This tool retrieves a single incident record by ID for informational purposes (status updates, review). It performs a read-only query operation with no data modification, deletion, or external action triggering. The verb 'get' combined with the read-only nature of incident retrieval (not creation, deletion, or state changes) confirms the Read category with low severity.

From the tool's definition Tool name 'incidents.get' and description 'Get a StillOnline incident by ID' and 'returns one incident record for follow-up status updates or review' clearly indicate retrieval of existing data with no side effects.

Questions about incidents.get

What does the incidents.get tool do? +

Get a StillOnline incident by ID. Despite the historical name, this returns one incident record for follow-up status updates or review. It is categorised as a Read tool in the Stillonline MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on incidents.get? +

Register the Stillonline MCP server in PolicyLayer and add a rule for incidents.get: 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 Stillonline. Nothing to install.

What risk level is incidents.get? +

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

Can I rate-limit incidents.get? +

Yes. Add a rate_limit block to the incidents.get 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 incidents.get completely? +

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

incidents.get is provided by the Stillonline MCP server (shenwell/stillonline-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.