AI agents call load_project_agent to retrieve information from Superkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
agentName | string | Yes | Agent name without .md extension. |
projectPath | string | — | Absolute path to the project root. Defaults to process.cwd(). |
Parameters from the server's own tool schema.
This tool performs a straightforward file read operation—it fetches and loads a markdown file from a known directory structure. There are no side effects, no data modification, no code execution, and no destructive operations. It is purely a retrieval mechanism, making it a Read category tool with low severity risk.
From the tool's definition The tool 'load_project_agent' retrieves a markdown file from a specific file path ({projectPath}/.agents/agents/{agentName}.md).
Attacks that exploit this kind of access
Loads a project-scoped agent markdown file from {projectPath}/.agents/agents/{agentName}.md. It is categorised as a Read tool in the Superkit MCP Server, which means it retrieves data without modifying state.
load_project_agent accepts 2 parameters: agentName, projectPath. Required: agentName. The full parameter table on this page comes from the server's own tool schema.
Register the Superkit MCP server in PolicyLayer and add a rule for load_project_agent: 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 Superkit. Nothing to install.
load_project_agent 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 load_project_agent 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 load_project_agent. 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.
load_project_agent is provided by the Superkit MCP server (superkit-mcp-server). 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 →