Low Risk

jina_search

Search the web. The response includes only partial contents of each web page. Use jina reader for full content.

How to control jina_search ↓

AI agents call jina_search to retrieve information from Jina AI MCP Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool queries web search results and returns data without side effects. It retrieves information only (partial web page contents), making it a Read operation. The low severity reflects that misuse would only expose publicly available information or potentially irrelevant search results, with no ability to modify systems, execute code, or cause financial harm.

From the tool's definition Tool name is 'jina_search' and description states 'Search the web. The response includes only partial contents of each web page.' This is a retrieval operation with no modification or execution of external systems.

Documented attack patterns abuse exactly the kind of access jina_search gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Jina AI MCP Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for jina_search:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "jina_search": {}
  }
}

jina_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Jina AI MCP Tools — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the jina_search tool do? +

Search the web. The response includes only partial contents of each web page. Use jina reader for full content. It is categorised as a Read tool in the Jina AI MCP Tools MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on jina_search? +

Register the Jina AI MCP Tools MCP server in PolicyLayer and add a rule for jina_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 Jina AI MCP Tools. Nothing to install.

What risk level is jina_search? +

jina_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit jina_search? +

Yes. Add a rate_limit block to the jina_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.

How do I block jina_search completely? +

Set action: deny in the PolicyLayer policy for jina_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.

What MCP server provides jina_search? +

jina_search is provided by the Jina AI MCP Tools MCP server (psycharch/jina-mcp-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Jina AI MCP Tools tool call.

Deterministic rules across all 3 Jina AI MCP Tools tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

3 Jina AI MCP Tools tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.