web_search
Neural and keyword web search over the live web. Returns ranked results with title, URL, publication date and author, optionally with the page text. Sub-second on repeat queries (5-minute cache).
This record as markdown: /tools/io-github-getgapup-gapup-mcp/web-search.md
What web_search does on Gapup Mcp
AI agents call web_search to retrieve information from Gapup Mcp 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 |
|---|---|---|---|
type | string | — | Search mode (default auto) |
async | boolean | — | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
query | string | Yes | The search query |
category | string | — | Restrict results to one kind of page |
numResults | integer | — | How many results (default 10) |
includeText | boolean | — | Include the page text in each result (default false) |
excludeDomains | array | — | |
includeDomains | array | — | |
startPublishedDate | string | — | ISO-8601 date; only pages published after it |
Parameters from the server's own tool schema.
Why web_search is rated Low
Queries and retrieves publicly available web data without side effects or modifications.
From the tool's definition web search, retrieves ranked results with title, URL, publication date
Attacks that exploit this kind of access
The rule that runs web_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gapup Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For web_search, this is the rule to start with:
web_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 Gapup Mcp, apply this rule, and every web_search call is checked against it from then on.
Questions about web_search
Neural and keyword web search over the live web. Returns ranked results with title, URL, publication date and author, optionally with the page text. Sub-second on repeat queries (5-minute cache). It is categorised as a Read tool in the Gapup Mcp MCP Server, which means it retrieves data without modifying state.
web_search accepts 9 parameters: type, async, query, category, numResults, includeText, excludeDomains, includeDomains, startPublishedDate. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Gapup MCP server in PolicyLayer and add a rule for web_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 Gapup Mcp. Nothing to install.
web_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 web_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 web_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.
web_search is provided by the Gapup MCP server (https://mcp.gapup.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gapup, and thousands of servers like it.
This server
Across the catalogue