create_research_plan

THE RISK

Medium Risk

Why create_research_plan needs a policy

This tool creates a research plan document/artifact, which is a reversible write operation. It retrieves data from SEC EDGAR and synthesizes it into a new research plan output, but does not execute transactions, delete data, or trigger external financial operations.

From the tool's definition Tool name contains 'create' and description states 'Create a comprehensive research plan', indicating it generates/creates new data artifacts. No execution of trades, deletion, or external operations.

Documented attack patterns abuse exactly the kind of access create_research_plan gives an agent:

POLICY

How to control create_research_plan

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_research_plan": {
      "limits": [
        {
          "counter": "create_research_plan_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_research_plan stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register SEC MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More SEC MCP tools

Execute parse_research_request Parse a natural language research request into MCP commands Execute perform_dcf_valuation Perform advanced DCF valuation with Monte Carlo simulation Read parse_xbrl_data Parse XBRL structured financial data from SEC filings Read parse_xbrl_financials Parse XBRL financial data from SEC filings with advanced metrics Read analyze_employee_sentiment Analyze employee sentiment and company culture indicators Read analyze_hiring_trends Analyze company hiring trends through job postings Read analyze_news_sentiment Analyze sentiment of news headlines using keyword analysis Read analyze_sentiment Perform advanced NLP sentiment analysis on earnings calls, news, and filings

All 62 SEC MCP tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about create_research_plan

What does the create_research_plan tool do? +

Create a comprehensive research plan for a stock. It is categorised as a Write tool in the SEC MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_research_plan? +

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

What risk level is create_research_plan? +

create_research_plan is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_research_plan? +

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

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

create_research_plan is provided by the SEC MCP server (luisrincon23/sec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every SEC MCP tool call.

Start from SEC MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →