get_project
AI agents call get_project to retrieve information from Keshro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' prefix is a strong indicator of a read-only retrieval operation. Without a description, confidence is reduced slightly, but the tool appears designed to query project state rather than execute code, modify data destructively, or commit financial resources. The absence of side-effect language and comparison with sibling management tools suggests minimal blast radius if misused by an agent.
From the tool's definition Tool name 'get_project' with no description indicates a retrieval operation. The naming convention aligns with sibling tools that perform state queries (add_task, complete_task, etc.), suggesting this fetches project data without modification.
Attacks that exploit this kind of access
get_project. It is categorised as a Read tool in the Keshro MCP MCP Server, which means it retrieves data without modifying state.
Register the Keshro MCP server in PolicyLayer and add a rule for get_project: 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 Keshro MCP. Nothing to install.
get_project 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 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. 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 is provided by the Keshro MCP server (jlewitt1/keshro-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 →