meta-tools.search
Search live Vee3 agent tools by keyword or short task description. Call this first when you are unsure which tool to use. Returns ranked matches with tool_name, summary, and cost for each hit. Use meta-tools.describe on the best match for full request and response schemas. Optional group_id narro...
This record as markdown: /tools/io-github-vee3io-vee3/meta-tools.search.md
What meta-tools.search does on Vee3
AI agents call meta-tools.search to retrieve information from Vee3 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | object | — | Maximum results to return (1–20). |
query | string | Yes | Keywords or short task description (for example `tiktok video comments` or `domain availability`). |
group_id | object | — | Optional group id to narrow results (for example `x-twitter`). |
Parameters from the server's own tool schema.
Why meta-tools.search is rated Low
This is a discovery/search tool that queries metadata about available tools on the Vee3 server and returns information. It performs no modifications, deletions, execution, or financial operations. It is a pure read operation against a tool registry or catalog.
From the tool's definition Tool description states it 'Search[es] live Vee3 agent tools by keyword' and 'Returns ranked matches with tool_name, summary, and cost for each hit.' The verb 'search' and 'returns' indicate data retrieval only.
Attacks that exploit this kind of access
The rule that runs meta-tools.search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Vee3, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For meta-tools.search, this is the rule to start with:
meta-tools.search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Vee3, apply this rule, and every meta-tools.search call is checked against it from then on.
Questions about meta-tools.search
Search live Vee3 agent tools by keyword or short task description. Call this first when you are unsure which tool to use. Returns ranked matches with tool_name, summary, and cost for each hit. Use meta-tools.describe on the best match for full request and response schemas. Optional group_id narrows results to one capability group. limit defaults to 8 (maximum 20). Cost = 0 tokens. It is categorised as a Read tool in the Vee3 MCP Server, which means it retrieves data without modifying state.
meta-tools.search accepts 3 parameters: limit, query, group_id. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Vee3 MCP server in PolicyLayer and add a rule for meta-tools.search: 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 Vee3. Nothing to install.
meta-tools.search 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 meta-tools.search 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 meta-tools.search. 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.
meta-tools.search is provided by the Vee3 MCP server (https://mcp.vee3.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Vee3, and thousands of servers like it.
This server
Across the catalogue