Retrieves a specific AGENTS.md file for providing AI with instructions and context.
AI agents call get_agents_instructions to retrieve information from Agents Library MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation with no side effects. It reads agent instruction files from a library, which is a Read operation. The blast radius is minimal—at worst, an AI agent accesses documentation or configuration information. There is no capability to modify, delete, or execute code through retrieval alone.
From the tool's definition Tool retrieves a specific AGENTS.md file; description states 'Retrieves' with no modification or execution capability. Sibling tool 'update_agents_file' indicates write operations are separate and distinct from this tool.
Attacks that exploit this kind of access
Retrieves a specific AGENTS.md file for providing AI with instructions and context. It is categorised as a Read tool in the Agents Library MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Agents Library MCP Server MCP server in PolicyLayer and add a rule for get_agents_instructions: 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 Agents Library MCP Server. Nothing to install.
get_agents_instructions 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_agents_instructions 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_agents_instructions. 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_agents_instructions is provided by the Agents Library MCP Server MCP server (nicholaswilde/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_agents_instructions is one line of Agents Library MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →