get_project_greeting
AI agents call get_project_greeting to retrieve information from Reachy Claude MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch greeting content for a project, which is a read-only operation with no capability to modify, delete, or execute external operations. The empty description reduces confidence slightly, but the naming pattern ('get_') and context (developer experience features) strongly suggest simple data retrieval. Severity is low as misuse would only expose or repeat greeting text.
From the tool's definition Tool name 'get_project_greeting' and context of a Reachy robot integration server suggest this retrieves or queries a greeting message associated with a project. No description provided, but naming convention aligns with data retrieval without side effects.
Attacks that exploit this kind of access
get_project_greeting. It is categorised as a Read tool in the Reachy Claude MCP MCP Server, which means it retrieves data without modifying state.
Register the Reachy Claude MCP server in PolicyLayer and add a rule for get_project_greeting: 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 Reachy Claude MCP. Nothing to install.
get_project_greeting 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_greeting 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_greeting. 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_greeting is provided by the Reachy Claude MCP server (mchardysam/reachy-claude-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 →