> ## Documentation Index
> Fetch the complete documentation index at: https://resq-dependabot-github-actions-github-actions-478e18be3d.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Prompts

<a id="resq_mcp.prompts" />

# resq\_mcp.prompts

MCP prompt templates for the ResQ server.

<a id="resq_mcp.prompts.re" />

## re

<a id="resq_mcp.prompts.FastMCPError" />

## FastMCPError

<a id="resq_mcp.prompts.mcp" />

## mcp

<a id="resq_mcp.prompts.incident_response_plan" />

#### incident\_response\_plan

```python theme={null}
@mcp.prompt()
def incident_response_plan(incident_id: str) -> str
```

Generate a structured prompt template for incident response planning.

Provides a framework for AI agents or human operators to systematically
analyze incidents and develop comprehensive response plans using
available MCP tools and resources.

Template Sections:

1. Situation Summary: Analyze current state and severity
2. Asset Allocation: Review and assign available resources
3. Risk Assessment: Evaluate hazards and constraints

**Arguments**:

* `incident_id` - The incident identifier to analyze (e.g., "INC-123").

**Returns**:

* `str` - Formatted prompt template with:
  * Analysis instructions
  * Tool references (get\_deployment\_strategy, resq://drones/active)
  * Expected output format

**Example**:

> > > prompt = incident\_response\_plan("INC-456")
> > >
> > > # Use with LLM:
> > >
> > > response = llm.complete(prompt)
> > >
> > > # LLM will call tools and produce structured response

Use Cases:

* AI-assisted crisis coordination (Spoon OS agent)
* Human operator decision support
* Training scenario generation
* Post-incident plan review

Integration:
Prompt references MCP tools and resources that the LLM can call:

* get\_deployment\_strategy(incident\_id) -> OptimizationStrategy
* resq://drones/active -> Fleet status
* Additional sector/swarm status tools as needed