AI agents call get_completions to retrieve information from MCP-TY without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a type checker for completion suggestions at a specific code position. It retrieves data (suggestions) with no side effects, reversible modifications, code execution, or destructive actions. It is purely informational, similar to other read-only tools on the server like 'get_type_info' and 'get_definition'.
From the tool's definition Tool name 'get_completions' and description 'Get code completion suggestions at position (1-based)' indicate a read-only operation that retrieves code suggestions without modifying any code or executing operations.
Attacks that exploit this kind of access
Get code completion suggestions at position (1-based). It is categorised as a Read tool in the MCP-TY MCP Server, which means it retrieves data without modifying state.
Register the MCP-TY MCP server in PolicyLayer and add a rule for get_completions: 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 MCP-TY. Nothing to install.
get_completions 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_completions 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_completions. 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_completions is provided by the MCP-TY MCP server (qinsehm1128/mcp-ty). 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 →