AI agents call get_project_by_key_tool 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 project information by key, which is a query operation with no side effects. It reads data from Jira without modifying, creating, or deleting anything. The 'get' prefix and sibling Read operations confirm this classification.
From the tool's definition Tool name 'get_project_by_key_tool' indicates a retrieval operation; sibling tools include 'get_issue_tool' and 'get_multiple_projects_tool' which are clearly Read operations, suggesting this follows the same pattern of fetching project data by identifier.
Attacks that exploit this kind of access
get_project_by_key_tool. 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 get_project_by_key_tool: 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.
get_project_by_key_tool 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_project_by_key_tool 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_project_by_key_tool. 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_project_by_key_tool is provided by the MCP Jira MCP server (tusharshahi/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 →