AI agents call get_kb_spaces to retrieve information from Jira without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a discovery/listing operation on Confluence knowledge base spaces with no side effects, no data modification, and no external state changes. It is purely informational to support downstream operations. This fits the Read category with low severity due to minimal blast radius—listing available spaces poses no risk of unintended data loss or system compromise.
From the tool's definition Tool name 'get_kb_spaces' and description 'List available Confluence/KB spaces' indicate a read-only query operation that retrieves/discovers space keys without modifying data.
Attacks that exploit this kind of access
List available Confluence/KB spaces. Useful for discovering space keys before searching. It is categorised as a Read tool in the Jira MCP Server, which means it retrieves data without modifying state.
Register the Jira MCP server in PolicyLayer and add a rule for get_kb_spaces: 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 Jira. Nothing to install.
get_kb_spaces 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_kb_spaces 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_kb_spaces. 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_kb_spaces is provided by the Jira MCP server (taraskhust/jira-mcp-server). 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 →