web_search
Search the web. Use this for current information: competitor research, market gaps, library docs, error messages, news. Provider defaults to DuckDuckGo (free, no key); set provider=google or provider=bing to use paid backends if GOOGLE_CSE_KEY+GOOGLE_CSE_CX or BING_API_KEY are configured. Returns...
This record as markdown: /tools/io-github-kivanccakmak-yaver/web-search.md
What web_search does on Yaver
AI agents call web_search to retrieve information from Yaver 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 | integer | — | Max results (default 10, max 25) |
query | string | Yes | The search query |
provider | string | — | duckduckgo (default) | google | bing | auto |
Parameters from the server's own tool schema.
Why web_search is rated Low
This tool retrieves search results from public web sources with no side effects. It is a pure query/read operation that gathers information. The use cases mentioned (competitor research, documentation lookup, error messages) are all informational. No write, execute, destructive, or financial operations are possible.
From the tool's definition Tool description explicitly states 'Search the web' and 'Returns title/url/snippet for each hit'. No modification, deletion, or execution capability is mentioned. It retrieves information only.
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 Yaver, 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 Yaver, apply this rule, and every web_search call is checked against it from then on.
Questions about web_search
Search the web. Use this for current information: competitor research, market gaps, library docs, error messages, news. Provider defaults to DuckDuckGo (free, no key); set provider=google or provider=bing to use paid backends if GOOGLE_CSE_KEY+GOOGLE_CSE_CX or BING_API_KEY are configured. Returns title/url/snippet for each hit. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
web_search accepts 3 parameters: limit, query, provider. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver 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 Yaver. 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 Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue