Call this before writing Vlossom UI code or when discovering what exists. Searches the compact component index by default; pass an explicit target for directives, composables, tokens, options, rules, or changelog entries. For target:'component' with an empty query, returns the compact component l...
AI agents call search_vlossom to retrieve information from Vlossom 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 | integer | — | |
query | string | — | |
intent | string | — | |
target | string | — | |
version | string | — | |
language | string | — | |
packageJson | string | — |
Parameters from the server's own tool schema.
Even though search_vlossom only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Call this before writing Vlossom UI code or when discovering what exists. Searches the compact component index by default; pass an explicit target for directives, composables, tokens, options, rules, or changelog entries. For target:'component' with an empty query, returns the compact component list. Then call get_vlossom_reference for exact APIs or scaffold_vlossom_code for a Vlossom-native starting point. It is categorised as a Read tool in the Vlossom MCP Server, which means it retrieves data without modifying state.
search_vlossom accepts 7 parameters: limit, query, intent, target, version, language, packageJson. The full parameter table on this page comes from the server's own tool schema.
Register the Vlossom MCP server in PolicyLayer and add a rule for search_vlossom: 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 Vlossom. Nothing to install.
search_vlossom 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_vlossom 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_vlossom. 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_vlossom is provided by the Vlossom MCP server (vlossom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.