Search graph nodes using contains, exact, or suffix matching.
AI agents call search_nodes to retrieve information from Trailmark MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from code repository graphs using pattern matching. It performs no modifications, deletions, or external operations. It is purely informational and read-only, fitting squarely into the Read category. The low severity reflects that search operations have minimal blast radius even if misused by an AI agent.
From the tool's definition Tool name is "search_nodes" and description states it performs "Search graph nodes using contains, exact, or suffix matching." These are query operations with no side effects.
Attacks that exploit this kind of access
Search graph nodes using contains, exact, or suffix matching. It is categorised as a Read tool in the Trailmark MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trailmark MCP Server MCP server in PolicyLayer and add a rule for search_nodes: 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 Trailmark MCP Server. Nothing to install.
search_nodes 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 search_nodes 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 search_nodes. 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.
search_nodes is provided by the Trailmark MCP Server MCP server (parsiya/trailmark-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →