get_party_cohesion
AI agents call get_party_cohesion to retrieve information from Open Assembly without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query legislative data (party voting patterns or cohesion statistics) from the Korean National Assembly Open API without modifying any data. The naming convention and context of sibling tools strongly suggest this is a data retrieval operation with no side effects. Low severity due to the public, non-sensitive nature of aggregate legislative statistics.
From the tool's definition Tool name 'get_party_cohesion' implies retrieval of cohesion metrics or voting data for political parties.
Attacks that exploit this kind of access
get_party_cohesion. It is categorised as a Read tool in the Open Assembly MCP Server, which means it retrieves data without modifying state.
Register the Open Assembly MCP server in PolicyLayer and add a rule for get_party_cohesion: 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 Open Assembly. Nothing to install.
get_party_cohesion 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_party_cohesion 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_party_cohesion. 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_party_cohesion is provided by the Open Assembly MCP server (kyusik-yang/open-assembly-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 →