AI agents call read_context 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 retrieves and displays source code content in a local context window. It performs no modifications, deletions, or external operations. It is purely informational, similar to other Read-category tools on the server like get_type_info, get_definition, and get_diagnostics. The blast radius of misuse is minimal: an agent could read unintended code sections but cannot modify or execute anything.
From the tool's definition Tool name is 'read_context' and description states it will 'Read code around a specific line with context' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Read code around a specific line with context. 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 read_context: 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.
read_context 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_context 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_context. 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_context 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 →