web_search

THE RISK

Low Risk

Why web_search needs a policy

Web search is a read-only operation that queries external data sources and returns results without creating, modifying, or deleting any data. The blast radius of misuse is minimal—an agent could retrieve irrelevant information or make inefficient queries, but cannot compromise data integrity or trigger financial/destructive actions.

From the tool's definition Tool name 'web_search' and description 'Searches the live web for current data' indicate a retrieval operation with no data modification or side effects.

Documented attack patterns abuse exactly the kind of access web_search gives an agent:

POLICY

How to control web_search

PolicyLayer is an MCP gateway — it sits between your AI agents and M3 Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for web_search:

policy.json

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

web_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register M3 Memory — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More M3 Memory tools

Destructive files_corpus_delete Delete a corpus's settings row. Cascade=True also deletes its Destructive files_entity_coalesce_unapply Reverse one coalescence cluster (drop edges, clear flags, strip Destructive retire_focus Clears the current system focus entry. Execute debug_bisect Automated git bisect placeholder. Execute files_extract_pending Drain leaves with extraction_status='pending' through the LLM extractor. Execute grok_ask Queries Grok 3 for real-time info from X and fast reasoning. Execute query_local_model Sends a complex reasoning task to the best available local/network LLM. Write debug_report Generate and persist a structured debugging report.

All 43 M3 Memory tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about web_search

What does the web_search tool do? +

Searches the live web for current data. It is categorised as a Read tool in the M3 Memory MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on web_search? +

Register the M3 Memory 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 M3 Memory. Nothing to install.

What risk level is web_search? +

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

Can I rate-limit web_search? +

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.

How do I block web_search completely? +

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.

What MCP server provides web_search? +

web_search is provided by the M3 Memory MCP server (skynetcmd/m3-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every M3 Memory tool call.

Start from M3 Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →