API URL에서 실제 GitHub 코드를 가져옴 (템플릿 리소스 사용)
AI agents call read_source_code to retrieve information from KIS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries/retrieves source code from GitHub via an API without modifying, executing, or deleting anything. It is a read-only data retrieval operation. Severity is low because obtaining source code presents minimal risk compared to execution or destructive operations, though context-dependent access controls on sensitive repositories could elevate concerns.
From the tool's definition Tool name 'read_source_code' and description 'API URL에서 실제 GitHub 코드를 가져옴' (retrieves actual GitHub code from API URL) indicate a retrieval operation with no modifications or side effects. Uses template resources to fetch code.
Attacks that exploit this kind of access
API URL에서 실제 GitHub 코드를 가져옴 (템플릿 리소스 사용). It is categorised as a Read tool in the KIS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KIS MCP Server MCP server in PolicyLayer and add a rule for read_source_code: 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 KIS MCP Server. Nothing to install.
read_source_code 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 read_source_code 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 read_source_code. 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.
read_source_code is provided by the KIS MCP Server MCP server (soyjefu/kis-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 →