find_similar_articles

Find articles thematically similar to a given article by cosine similarity over Voyage AI embeddings. Use after an article has been surfaced (via search, get_recent_reads, or an @rewind://article/{id} mention) when the user asks

Server Rewind rewind-mcp-server
Category Read
Risk class Low
Parameters 00 required

What find_similar_articles does on Rewind

AI agents call find_similar_articles 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.

Why find_similar_articles needs a policy

This tool retrieves and searches data (finding similar articles) without creating, modifying, deleting, or executing operations. It is analogous to a search or query function that returns information based on vector similarity, placing it squarely in the Read category with low severity.

From the tool's definition Tool performs similarity search over embeddings using cosine similarity to 'find articles thematically similar' — a read-only query operation with no side effects. The description explicitly states it is used 'when the user asks' to retrieve related content.

Questions about find_similar_articles

What does the find_similar_articles tool do? +

Find articles thematically similar to a given article by cosine similarity over Voyage AI embeddings. Use after an article has been surfaced (via search, get_recent_reads, or an @rewind://article/{id} mention) when the user asks. It is categorised as a Read tool in the Rewind MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_similar_articles? +

Register the Rewind MCP server in PolicyLayer and add a rule for find_similar_articles: 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.

What risk level is find_similar_articles? +

find_similar_articles is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit find_similar_articles? +

Yes. Add a rate_limit block to the find_similar_articles 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.

How do I block find_similar_articles completely? +

Set action: deny in the PolicyLayer policy for find_similar_articles. 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.

What MCP server provides find_similar_articles? +

find_similar_articles 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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.