Fetch authoritative docs for exactly ONE MTA:SA function/event by canonical name. Preferred over manual web browsing. For multiple names, use get_multiple_function_docs in one call.
AI agents call get_function_docs to retrieve information from MTA:SA Documentation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a lookup/query of existing documentation. It retrieves information without modifying, executing, or deleting anything. The action is purely informational and read-only. The blast radius of misuse is negligible—an agent could retrieve irrelevant or excessive documentation, but no damage can occur. Severity is low because documentation lookup poses minimal risk regardless of what is queried.
From the tool's definition Tool 'get_function_docs' retrieves documentation for a single MTA:SA function/event by canonical name. Description states 'Fetch authoritative docs'—a retrieval operation with no mention of side effects, data modification, or destructive actions.
Attacks that exploit this kind of access
Fetch authoritative docs for exactly ONE MTA:SA function/event by canonical name. Preferred over manual web browsing. For multiple names, use get_multiple_function_docs in one call. It is categorised as a Read tool in the MTA:SA Documentation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MTA:SA Documentation MCP Server MCP server in PolicyLayer and add a rule for get_function_docs: 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 MTA:SA Documentation MCP Server. Nothing to install.
get_function_docs 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_function_docs 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_function_docs. 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_function_docs is provided by the MTA:SA Documentation MCP Server MCP server (mtasa-docs-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 →