CODEMESH STEP 2: Get TypeScript type definitions for specific tools you want to use in your code. This generates the server object interfaces you
AI agents call get-tool-apis to retrieve information from Codemesh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns type definitions and API schemas for other tools. It has no side effects, creates no data, executes no code, and modifies no state. It is a read-only introspection/metadata retrieval operation. The low severity reflects minimal blast radius: an agent misusing this tool could only access or learn about API schemas, posing no direct risk to systems or data.
From the tool's definition Tool name 'get-tool-apis' and description indicate it 'generates the server object interfaces' and 'Get TypeScript type definitions' — purely retrieves metadata/schema information about available tools.
Documented attack patterns abuse exactly the kind of access get-tool-apis gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Codemesh, and nothing reaches the server without passing your rules. This is the rule we recommend for get-tool-apis:
{
"version": "1",
"default": "deny",
"tools": {
"get-tool-apis": {}
}
}get-tool-apis 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.
CODEMESH STEP 2: Get TypeScript type definitions for specific tools you want to use in your code. This generates the server object interfaces you. It is categorised as a Read tool in the Codemesh MCP Server, which means it retrieves data without modifying state.
Register the Codemesh MCP server in PolicyLayer and add a rule for get-tool-apis: 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 Codemesh. Nothing to install.
get-tool-apis 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-tool-apis 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-tool-apis. 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-tool-apis is provided by the Codemesh MCP server (kiliman/codemesh). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Codemesh, 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.
13 Codemesh tools catalogued and risk-classified — across an index of 43,000+ MCP servers.