getObject
AI agents call getObject to retrieve information from Trellis MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name 'getObject' indicates a read operation that retrieves project objects (tasks, features, epics, or projects) from the file-backed storage system. No description is available, which reduces confidence slightly, but context from the server's function (hierarchical project management) and sibling tools (claimNextTask, completeTask, updateObject) confirms this is a query/fetch operation with no side effects.
From the tool's definition Tool name 'getObject' and pattern consistency with 'listBacklog' and 'updateObject' suggest a data retrieval operation. The Trellis MCP server stores project data in Markdown-backed files, and 'getObject' follows standard CRUD naming conventions for retrieval.
Attacks that exploit this kind of access
getObject. It is categorised as a Read tool in the Trellis MCP MCP Server, which means it retrieves data without modifying state.
Register the Trellis MCP server in PolicyLayer and add a rule for getObject: 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 Trellis MCP. Nothing to install.
getObject 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 getObject 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 getObject. 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.
getObject is provided by the Trellis MCP server (langadventurellc/trellis-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 →