parlament_search_members
AI agents call parlament_search_members to retrieve information from Pypi:parlament without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches/retrieves member information from a public parliamentary database with no authentication required. It performs a read-only query with no data modification, deletion, or execution capabilities. The blast radius of misuse is minimal since it only exposes publicly available parliamentary member data. Severity is low because there are no side effects and the data is non-sensitive public information.
From the tool's definition Tool name 'parlament_search_members' and server context indicate querying of member data from Swiss Federal Parliament via public API.
Attacks that exploit this kind of access
parlament_search_members. It is categorised as a Read tool in the Pypi:parlament MCP Server, which means it retrieves data without modifying state.
Register the Pypi:parlament MCP server in PolicyLayer and add a rule for parlament_search_members: 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 Pypi:parlament. Nothing to install.
parlament_search_members 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 parlament_search_members 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 parlament_search_members. 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.
parlament_search_members is provided by the Pypi:parlament MCP server (malkreide/parlament-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 →