get_act
AI agents call get_act 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.
This tool retrieves or queries legislative data with no side effects. It fits the Read category—it appears to fetch sections or full text of acts from a legal database. No modifications, execution, deletion, or financial operations are implied. The low severity reflects that misuse would only expose legislative information, which is typically public.
From the tool's definition Tool name 'get_act' with sibling tools 'get_section', 'get_statistics', 'list_acts', and 'search_acts' indicate data retrieval operations.
Attacks that exploit this kind of access
get_act. 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 get_act: 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.
get_act 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 get_act 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 get_act. 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.
get_act 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 →