search_acts
AI agents call search_acts to retrieve information from Bangladesh Law MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool operates within a legislation reference server where all sibling tools perform non-destructive data retrieval. There is no indication of write, execute, delete, or financial capabilities. The description is empty, but the context of the server (querying Bangladeshi legislation) and the naming pattern of related tools establish this as a Read operation with high confidence.
From the tool's definition Tool name 'search_acts' with no description provided; sibling tools on this server (get_act, get_section, get_statistics, list_acts) are all read-only query operations that retrieve legislative text without modification.
Attacks that exploit this kind of access
search_acts. It is categorised as a Read tool in the Bangladesh Law MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bangladesh Law MCP Server MCP server in PolicyLayer and add a rule for search_acts: 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 Bangladesh Law MCP Server. Nothing to install.
search_acts 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_acts 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_acts. 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_acts is provided by the Bangladesh Law MCP Server MCP server (rubaiyatemon/bangladesh-law-mcp). 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 →