AI agents call jira_get_projects to retrieve information from Mcp Jira without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists project metadata without creating, modifying, deleting, or executing operations. The 'get' verb and 'List' action in the description confirm it is a read operation. Severity is low because project enumeration is non-destructive reconnaissance that poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'jira_get_projects' and description 'List all Jira projects accessible' indicate a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
List all Jira projects accessible with the configured credentials. It is categorised as a Read tool in the Mcp Jira MCP Server, which means it retrieves data without modifying state.
Register the Mcp Jira MCP server in PolicyLayer and add a rule for jira_get_projects: 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 Mcp Jira. Nothing to install.
jira_get_projects 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 jira_get_projects 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 jira_get_projects. 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.
jira_get_projects is provided by the Mcp Jira MCP server (renan1fps/mcp-jira). 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 →