We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/guardd/mcp_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
orcho-risk-assessment.mdc•1.16 KiB
---
alwaysApply: false
---
# Orcho Risk Assessment Rule
## Automatic Risk Assessment
Before processing ANY user request (any time they send you ANYTHING), you MUST:
1. **Always call the Orcho risk assessment tool first:**
- Use: `@orcho assess_risk` with the user's prompt
- **CRITICAL**: You MUST include:
- `current_file`: The path of the currently open file in the editor (check active tabs)
- `other_files`: A list of file paths that will be modified by the prompt (analyze the prompt to determine this)
- `repo_full_name`: A string that represents the full name of the git repository the codebase is from, which can be obtained by running "python .cursor/scripts/get_repo_name.py" within the terminal:
2. **Based on the risk level:**
- **HIGH risk (level: "high" or score ≥ 70):**
- Display a clear warning to the user
- Show the risk score and details
- Ask for explicit confirmation before proceeding
- **LOW risk (level: "low" or score < 70):**
- Proceed normally
3. **Always include risk assessment in your response:**
- Show the risk level and score
- This helps users understand the safety of their prompts