AI agents call search_harnesses to retrieve information from Loadbay without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | max results, default 20 |
query | string | — | free-text over name, author, summary, integrations |
trait | string | — | require a capability trait |
domain | string | — | domain key: trading | coding | browser | productivity | data | social | health | science | gaming | media | robotics |
Parameters from the server's own tool schema.
This tool retrieves and filters data from a catalog without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with no side effects. The low severity reflects minimal risk even if misused—an AI agent could only retrieve information from the public catalog.
From the tool's definition Tool name is 'search_harnesses' and description states it 'Search[es] the Loadbay catalog' with 'Filter by free-text query, domain, and/or capability trait.' These are purely query operations with no mutation, deletion, or execution of external code.
Attacks that exploit this kind of access
Search the Loadbay catalog of harnesses for AI agents. Filter by free-text query, domain, and/or capability trait. It is categorised as a Read tool in the Loadbay MCP Server, which means it retrieves data without modifying state.
search_harnesses accepts 4 parameters: limit, query, trait, domain. The full parameter table on this page comes from the server's own tool schema.
Register the Loadbay MCP server in PolicyLayer and add a rule for search_harnesses: 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 Loadbay. Nothing to install.
search_harnesses 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 search_harnesses 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 search_harnesses. 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.
search_harnesses is provided by the Loadbay MCP server (https://loadbay.xyz/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_harnesses is one line of Loadbay's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →