Score and rank eBay listings using PartsTable's 5-factor composite scoring engine. Factors: Price (30%), Vendor Trust (25%), Distance (20%), Condition (15%), Quantity (10%). Vendor trust scores are looked up from IQreseller purchase history (435 vendors). Distance is calculated from warehouse ZIP...
Risk signalsHigh parameter count (28 properties)
Part of the PartsTable server.
Free to start. No card required.
AI agents call score-listing to retrieve information from PartsTable 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 score-listing 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.
{
"version": "1",
"default": "deny",
"tools": {
"score-listing": {}
}
}See the full PartsTable policy for all 9 tools.
These attack patterns abuse exactly the kind of access score-listing gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Score and rank eBay listings using PartsTable's 5-factor composite scoring engine. Factors: Price (30%), Vendor Trust (25%), Distance (20%), Condition (15%), Quantity (10%). Vendor trust scores are looked up from IQreseller purchase history (435 vendors). Distance is calculated from warehouse ZIP to seller location using haversine formula. Condition signals are extracted from listing text (warranty, tested, ships today). Returns items sorted by composite score (0-100) with full factor breakdown.. It is categorised as a Read tool in the PartsTable MCP Server, which means it retrieves data without modifying state.
Register the PartsTable MCP server in PolicyLayer and add a rule for score-listing: 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 PartsTable. Nothing to install.
score-listing 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 score-listing 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 score-listing. 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.
score-listing is provided by the PartsTable MCP server (https://mcp.partstable.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 PartsTable tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.