Low Risk

suggest_params

自然文の要件と designId から、クライアント AI(Sampling)で generate_pdf_sync 用の params JSON を下書きします。【Sampling 必須】claude.ai 等の Sampling 非対応クライアントでは自動生成できず、その場合はパラメータスキーマをそのまま返すので手動で params を埋めてください。パラメータ構造の確認だけが目的なら get_design_parameters を使ってください。サーバー側 API キー不要。生成された params は必ずユーザー承認のうえ generate_pdf_sync に渡してください。

Part of the ReportFlow server.

suggest_params is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE REPORTFLOW →

Free to start. No card required.

AI agents call suggest_params to retrieve information from ReportFlow without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though suggest_params only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "suggest_params": {}
  }
}

See the full ReportFlow policy for all 5 tools.

Get this rule live on your own ReportFlow server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY REPORTFLOW →

These attack patterns abuse exactly the kind of access suggest_params gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so suggest_params only ever does what you allow.

SECURE REPORTFLOW →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the suggest_params tool do? +

自然文の要件と designId から、クライアント AI(Sampling)で generate_pdf_sync 用の params JSON を下書きします。【Sampling 必須】claude.ai 等の Sampling 非対応クライアントでは自動生成できず、その場合はパラメータスキーマをそのまま返すので手動で params を埋めてください。パラメータ構造の確認だけが目的なら get_design_parameters を使ってください。サーバー側 API キー不要。生成された params は必ずユーザー承認のうえ generate_pdf_sync に渡してください。. It is categorised as a Read tool in the ReportFlow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on suggest_params? +

Register the ReportFlow MCP server in PolicyLayer and add a rule for suggest_params: 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 ReportFlow. Nothing to install.

What risk level is suggest_params? +

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

Can I rate-limit suggest_params? +

Yes. Add a rate_limit block to the suggest_params 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 suggest_params completely? +

Set action: deny in the PolicyLayer policy for suggest_params. 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 suggest_params? +

suggest_params is provided by the ReportFlow MCP server (reportflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ReportFlow tool call.

Deterministic rules across all 5 ReportFlow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.