Update default search engines and persist to .env
AI agents use set_engines to create or update resources in Mcp Open Webresearch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Open Webresearch environment.
This tool creates or modifies configuration data (search engine settings) that is persisted to a file (.env), making it a Write operation. The severity is medium because misconfiguration could redirect searches to malicious engines or compromise privacy/security, but it does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition 'Update default search engines and persist to .env' — modifies persistent configuration data stored in the .env file.
Attacks that exploit this kind of access
Update default search engines and persist to .env. It is categorised as a Write tool in the Mcp Open Webresearch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Open Webresearch MCP server in PolicyLayer and add a rule for set_engines: 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 Mcp Open Webresearch. Nothing to install.
set_engines is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_engines 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 set_engines. 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.
set_engines is provided by the Mcp Open Webresearch MCP server (rinaldowouterson/mcp-open-webresearch). 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 →