Low Risk

search_with_mode

search_with_mode

How to control search_with_mode ↓

AI agents call search_with_mode to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Despite the empty description, the name and server's purpose as a code intelligence framework indicate this is a search function that retrieves code information without modifying data. Sibling tools like 'analyze_perf', 'audit_config' further confirm read-centric operations. No indicators of destructive, financial, or execute-level actions.

From the tool's definition Tool name 'search_with_mode' suggests a querying/search operation typical of code intelligence tools. The server context emphasizes 'navigation, impact analysis, refactoring, security scanning' where search is a fundamental read-only operation for inspecting…

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_with_mode": {}
  }
}

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

  1. Create a free account and register Trace — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the search_with_mode tool do? +

search_with_mode. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_with_mode? +

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

What risk level is search_with_mode? +

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

Can I rate-limit search_with_mode? +

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

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

search_with_mode is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Trace tool call.

Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.