AI agents call get_instructions to retrieve information from CodeForge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and lack of modification indicators in the name imply this is a read operation that retrieves data without side effects. Confidence is moderate because the description is empty, preventing confirmation of exact behavior. Within the server's ecosystem of more dangerous tools (execute_code, delete_skill, update_skill), this appears to be the least risky.
From the tool's definition The tool name 'get_instructions' with no description suggests a retrieval action, consistent with fetching or reading instructions. The server context includes Read operations like 'list_apis', supporting this classification.
Documented attack patterns abuse exactly the kind of access get_instructions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeForge MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_instructions:
{
"version": "1",
"default": "deny",
"tools": {
"get_instructions": {}
}
}get_instructions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_instructions. It is categorised as a Read tool in the CodeForge MCP MCP Server, which means it retrieves data without modifying state.
Register the CodeForge MCP server in PolicyLayer and add a rule for get_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 CodeForge MCP. Nothing to install.
get_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_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_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_instructions is provided by the CodeForge MCP server (max-rousseau/codeforge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeForge MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 CodeForge MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.