AI agents call list_all_algorithm to retrieve information from TG_MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that returns information about built-in algorithms. It has no side effects, makes no modifications to data, and does not execute arbitrary code or commands. The operation is informational and safe for AI agents to invoke without risk of unintended consequences. Classified as Read with low severity.
From the tool's definition Tool name 'list_all_algorithm' and description 'List available built-in algorithms' indicate a query/enumeration operation that retrieves metadata about available algorithms without modifying data or executing queries.
Attacks that exploit this kind of access
MCP tool: List available built-in algorithms. It is categorised as a Read tool in the TG_MCP MCP Server, which means it retrieves data without modifying state.
Register the TG_ MCP server in PolicyLayer and add a rule for list_all_algorithm: 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 TG_MCP. Nothing to install.
list_all_algorithm 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 list_all_algorithm 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 list_all_algorithm. 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.
list_all_algorithm is provided by the TG_ MCP server (muzain187/tg_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 →