Main Sundr decision engine. Analyzes whether to REPAIR or REPLACE a broken device. Analyze whether to REPAIR, REPLACE, or sell a broken device. The core Sundr decision engine. USE THIS TOOL WHEN USERS ASK: - "Should I repair my [phone/laptop/tablet]?" - "Is it worth fixing my [device]?" - "Repa...
Part of the Sundr Repair Advisor MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call repair_decision to retrieve information from Sundr Repair Advisor without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though repair_decision only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
repair_decision:
rules:
- action: allow See the full Sundr Repair Advisor policy for all 25 tools.
Agents calling read-class tools like repair_decision have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Main Sundr decision engine. Analyzes whether to REPAIR or REPLACE a broken device. Analyze whether to REPAIR, REPLACE, or sell a broken device. The core Sundr decision engine. USE THIS TOOL WHEN USERS ASK: - "Should I repair my [phone/laptop/tablet]?" - "Is it worth fixing my [device]?" - "Repair or replace my [device]?" - "Can I fix my broken [device]?" - "What should I do about my broken [device]?" - "Is my [device] worth repairing?" - "Should I buy a new [device] or fix this one?" - "My [device] is broken, what are my options?" - "Is repair cheaper than buying new?" - "Fix or buy new?" - "How much would it cost to fix [device]?" COVERS: Smartphones (iPhone, Samsung, Pixel), laptops (MacBook, Dell, Lenovo), tablets (iPad), smartwatches, headphones, gaming consoles, TVs, printers, cameras, washing machines, dryers, dishwashers, refrigerators, vacuums, air conditioners, kitchen appliances (blenders, coffee makers, microwaves). RETURNS: Repair recommendation with confidence score, cost-benefit analysis, CO2 environmental savings, local repair shop options, DIY repair links, and refurbished alternatives with affiliate links.. It is categorised as a Read tool in the Sundr Repair Advisor MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for repair_decision. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Sundr Repair Advisor MCP server.
repair_decision is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the repair_decision rule in your Intercept 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 Intercept policy for repair_decision. 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.
repair_decision is provided by the Sundr Repair Advisor MCP server (sundr-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept