AI agents call get_project_agents_md to retrieve information from Openl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and loads documentation (AGENTS.md guidance) for a project. It performs no data modification, deletion, code execution, or financial operations. The 'get' verb combined with the passive description 'Load...as a single aggregated markdown document' confirms this is a read-only operation with no side effects.
From the tool's definition Tool name 'get_project_agents_md' uses 'get' prefix indicating retrieval. Description states 'Load the AGENTS.md guidance' and 'as a single aggregated markdown document', describing a read operation that retrieves and presents documentation without…
Attacks that exploit this kind of access
Load the AGENTS.md guidance that applies to a project as a single aggregated markdown document. Starting at the project directory — or the optional. It is categorised as a Read tool in the Openl MCP Server, which means it retrieves data without modifying state.
Register the Openl MCP server in PolicyLayer and add a rule for get_project_agents_md: 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 Openl. Nothing to install.
get_project_agents_md 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_agents_md 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_agents_md. 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_agents_md is provided by the Openl MCP server (openl-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 →