Low Risk

calculate-similarity

计算两个PDF文档的相似度

How to control calculate-similarity ↓

AI agents call calculate-similarity to retrieve information from Pdf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This tool retrieves and analyzes content from PDFs to produce a similarity metric. It has no side effects—it does not modify, delete, or execute code. It fits the Read category as it queries/analyzes document data without irreversible or code-execution consequences. Severity is low because misuse would only expose analysis results, not enable data destruction, financial impact, or arbitrary code execution.

From the tool's definition calculate-similarity computes similarity between two PDF documents; the description '计算两个PDF文档的相似度' (calculate the similarity of two PDF documents) indicates a read-only analytical operation with no modification, deletion, or execution of external code.

Documented attack patterns abuse exactly the kind of access calculate-similarity gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Pdf, and nothing reaches the server without passing your rules. This is the rule we recommend for calculate-similarity:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "calculate-similarity": {}
  }
}

calculate-similarity is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Pdf — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the calculate-similarity tool do? +

计算两个PDF文档的相似度. It is categorised as a Read tool in the Pdf MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on calculate-similarity? +

Register the Pdf MCP server in PolicyLayer and add a rule for calculate-similarity: 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 Pdf. Nothing to install.

What risk level is calculate-similarity? +

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

Can I rate-limit calculate-similarity? +

Yes. Add a rate_limit block to the calculate-similarity 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 calculate-similarity completely? +

Set action: deny in the PolicyLayer policy for calculate-similarity. 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 calculate-similarity? +

calculate-similarity is provided by the Pdf MCP server (saury1120/pdf-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pdf tool call.

Deterministic rules across all 9 Pdf tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

9 Pdf tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.