Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives. For best results, provide multiple search queries that explore different aspects of your topic. You can use expand_query to help generate diverse queries, or create them yourself.
AI agents call parallel_search_web to retrieve information from Jina AI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
timeout | number | — | Timeout in milliseconds for all searches |
searches | array | — | Array of search configurations to execute in parallel (maximum 5 searches for optimal performance) |
Parameters from the server's own tool schema.
This tool queries external web search engines and retrieves results. Like a traditional search operation, it has no side effects beyond fetching and returning publicly available information. The 'parallel' execution method does not elevate the category—it remains a Read operation. Confidence is high given the explicit mention of 'searches' and the lack of any write, execute, or destructive capabilities.
From the tool's definition Tool performs 'web searches' which are retrieval operations that return search results without modifying data. Description emphasizes 'search' and 'coverage' of information, typical Read semantics.
Risk signalsAccepts freeform code/query input (searches[].query)
Documented attack patterns abuse exactly the kind of access parallel_search_web gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jina AI, and nothing reaches the server without passing your rules. This is the rule we recommend for parallel_search_web:
{
"version": "1",
"default": "deny",
"tools": {
"parallel_search_web": {}
}
}parallel_search_web is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run multiple web searches in parallel for comprehensive topic coverage and diverse perspectives. For best results, provide multiple search queries that explore different aspects of your topic. You can use expand_query to help generate diverse queries, or create them yourself. It is categorised as a Read tool in the Jina AI MCP Server, which means it retrieves data without modifying state.
parallel_search_web accepts 2 parameters: timeout, searches. The full parameter table on this page comes from the server's own tool schema.
Register the Jina AI MCP server in PolicyLayer and add a rule for parallel_search_web: 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 Jina AI. Nothing to install.
parallel_search_web 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 parallel_search_web 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 parallel_search_web. 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.
parallel_search_web is provided by the Jina AI MCP server (jina). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jina AI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Jina AI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.