bing_search
Search Bing web results. Returns normalized Bing web search results for a query string, including organic results, optional context panel data, related queries, people-also-ask questions, news modules, video modules, and page-based pagination. Empty optional blocks are omitted from the JSON respo...
This record as markdown: /tools/crawlora-mcp/bing-search.md
What bing_search does on Crawlora
AI agents call bing_search to retrieve information from Crawlora 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 |
|---|---|---|---|
q | string | Yes | Search query |
lang | string | — | Bing UI language; defaults to en-us |
page | integer | — | 1-based page number; defaults to 1 |
count | integer | — | Results per page; defaults to 10, clamped to 1..50 |
country | string | — | Two-letter country code; defaults to us |
Parameters from the server's own tool schema.
Why bing_search is rated Low
Even though bing_search only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs bing_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crawlora, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bing_search, this is the rule to start with:
bing_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 Crawlora, apply this rule, and every bing_search call is checked against it from then on.
Questions about bing_search
Search Bing web results. Returns normalized Bing web search results for a query string, including organic results, optional context panel data, related queries, people-also-ask questions, news modules, video modules, and page-based pagination. Empty optional blocks are omitted from the JSON response. Locale defaults to country=us and lang=en-us. Results are fetched with a Chrome-impersonated request client and return 503 when Bing serves a challenge page or unusable HTML. Queries that use the site: operator (for example site:gov.hu) are not supported: Bing serves a bot-verification challenge for them, so they are rejected with 400 before any request is made. Use the Google search endpoint (/api/v1/google/search) for domain-restricted searches. It is categorised as a Read tool in the Crawlora MCP Server, which means it retrieves data without modifying state.
bing_search accepts 5 parameters: q, lang, page, count, country. Required: q. The full parameter table on this page comes from the server's own tool schema.
Register the Crawlora MCP server in PolicyLayer and add a rule for bing_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 Crawlora. Nothing to install.
bing_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 bing_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 bing_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.
bing_search is provided by the Crawlora MCP server (crawlora-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crawlora, and thousands of servers like it.
This server
Across the catalogue