指定 ID のナレッジ記事の本文 (Markdown) を含む全フィールドを返す。
AI agents call get_knowledge_article to retrieve information from Poranos Mcp Ainpc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and queries data (fetches a knowledge article by ID) without creating, modifying, or deleting anything. This is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_knowledge_article' and description indicating it 'returns all fields including the body (Markdown) of a knowledge article' — a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
指定 ID のナレッジ記事の本文 (Markdown) を含む全フィールドを返す。. It is categorised as a Read tool in the Poranos Mcp Ainpc MCP Server, which means it retrieves data without modifying state.
Register the Poranos Mcp Ainpc MCP server in PolicyLayer and add a rule for get_knowledge_article: 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 Poranos Mcp Ainpc. Nothing to install.
get_knowledge_article 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_knowledge_article 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_knowledge_article. 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_knowledge_article is provided by the Poranos Mcp Ainpc MCP server (kkoba23/poranos-mcp-ainpc). 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 →