Fetch one saved article by id, returning its full body, metadata, and highlights. Use this whenever the user asks what an article says, wants a summary, asks about a specific passage, or needs content past the first ~3000 chars of excerpt. Also use this as the natural follow-up after
AI agents call get_article to retrieve information from Rewind without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries stored article data without any side effects. It returns article body, metadata, and highlights but does not create, modify, delete, or execute anything. It is a pure data retrieval operation, making it a Read category tool with low severity since misuse would only expose existing personal article data the user has already saved.
From the tool's definition Tool description states 'Fetch one saved article by id, returning its full body, metadata, and highlights.' The verb 'Fetch' and the read-only nature of retrieving article content with no modification capability are clear indicators.
Attacks that exploit this kind of access
Fetch one saved article by id, returning its full body, metadata, and highlights. Use this whenever the user asks what an article says, wants a summary, asks about a specific passage, or needs content past the first ~3000 chars of excerpt. Also use this as the natural follow-up after. It is categorised as a Read tool in the Rewind MCP Server, which means it retrieves data without modifying state.
Register the Rewind MCP server in PolicyLayer and add a rule for get_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 Rewind. Nothing to install.
get_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_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_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_article is provided by the Rewind MCP server (rewind-mcp-server). 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 →