web_research

SERVERDialogbrain SOURCEhttps://api.dialogbrain.com/mcp

Low RISK CLASS

Category Read

Parameters 41 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-saloprj-dialogbrain/web-research.md

WHAT IT DOES

What web_research does on Dialogbrain

AI agents call web_research to retrieve information from Dialogbrain 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
`mode`	string	—	Research depth: 'quick' (default, seconds, cheapest), 'pro' (harder questions, better sourcing), 'deep' (autonomous multi-step research, takes minutes — only wh
`query`	string	Yes	Research question. Specific scoped questions outperform vague keywords.
`domains`	array	—	Restrict search to these domains (max 10), e.g. ['coindesk.com', 'cointelegraph.com']. Prefix with '-' to exclude a domain.
`recency`	string	—	Only use sources from this window. Omit for no limit.

Parameters from the server's own tool schema.

RISK

Why web_research is rated Low

web_research retrieves and aggregates publicly available web data to answer questions. It has no side effects, does not modify any data, execute commands, or trigger external operations beyond information fetching. The 'deep' mode parameter merely controls search depth/duration, not execution capability. This is a straightforward Read operation with minimal security risk.

From the tool's definition Tool performs information retrieval from web sources with 'synthesized answer' and 'citations array' — no modification, deletion, or execution capabilities.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs web_research safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For web_research, this is the rule to start with:

web_research Allowed

web_research is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "web_research": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every web_research call is checked against it from then on.

FAQ

Questions about web_research

What does the web_research tool do? +

Answer a research question from live web sources in one call — returns a synthesized answer with numbered [N] citation markers and a citations array of {url, title, index}. Supports recency and domain filters. Use for questions needing current, sourced information (news about a company, market state, comparisons). For raw search result links use web.search; mode='deep' runs minutes-long exhaustive research — only when explicitly requested. It is categorised as a Read tool in the Dialogbrain MCP Server, which means it retrieves data without modifying state.

What parameters does web_research accept? +

web_research accepts 4 parameters: mode, query, domains, recency. Required: query. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on web_research? +

Register the Dialogbrain MCP server in PolicyLayer and add a rule for web_research: 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 Dialogbrain. Nothing to install.

What risk level is web_research? +

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

Can I rate-limit web_research? +

Yes. Add a rate_limit block to the web_research 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 web_research completely? +

Set action: deny in the PolicyLayer policy for web_research. 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 web_research? +

web_research is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Dialogbrain, and thousands of servers like it.

This server

All 225 Dialogbrain tools →

Across the catalogue

web_search on Azure AI Agent Service + Azure AI Search MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →