web__local_search

Multi-source web research with citations. Returns a synthesized answer with numbered [^1] markers and a citations array of {url, title, snippet, index}. Use for evidence-backed synthesis (competitive analysis, regulatory summary, whitepaper section). For quick fact lookups use web.search instead.

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

Low RISK CLASS

Category Read

Parameters 31 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--local-search.md

WHAT IT DOES

What web__local_search does on Dialogbrain

AI agents call web__local_search 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
`query`	string	Yes	Research question. Specific scoped questions outperform vague keywords.
`language`	string	—	Search language hint (BCP-47, e.g. 'en', 'ru'). Defaults to 'en'. The synthesis output language matches the query language regardless.
`num_sources`	integer	—	How many top search results to fetch and synthesize (1-4, default 4). Lower = faster + cheaper, higher = more comprehensive.

Parameters from the server's own tool schema.

RISK

Why web__local_search is rated Low

web__local_search retrieves and synthesizes information from web sources without any side effects. It reads data and returns citations, answers, and snippets—classic Read behavior. No data is modified, deleted, executed, or financially committed. The tool is explicitly positioned as an alternative to quick fact lookups with no capability to alter state.

From the tool's definition Tool description states it 'Returns a synthesized answer with numbered markers and a citations array' and is used for 'evidence-backed synthesis' and 'fact lookups'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs web__local_search 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__local_search, this is the rule to start with:

web__local_search Allowed

web__local_search 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__local_search": {}
  }
}

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__local_search call is checked against it from then on.

FAQ

Questions about web__local_search

What does the web__local_search tool do? +

What parameters does web__local_search accept? +

web__local_search accepts 3 parameters: query, language, num_sources. 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__local_search? +

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

What risk level is web__local_search? +

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

Can I rate-limit web__local_search? +

Yes. Add a rate_limit block to the web__local_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 web__local_search completely? +

Set action: deny in the PolicyLayer policy for web__local_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 web__local_search? +

web__local_search 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 →search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server →search_channel on YouTube MCP Server → The MCP Attack Database →

Guides

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