// SCAN REPORT

OpenFinClaw CLI

21 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

5 can modify or destroy data

16 read-only

21 tools total

Community server · catalogue entry verified 11/06/2026

How to control OpenFinClaw CLI ↓

TOOL MAP

What OpenFinClaw CLI exposes to your agents

Read (16) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous OpenFinClaw CLI tools

Destructive · High fin_deepagent_threads Because the tool spans multiple categories (Read for list/get, Write for create, Destructive for delete), the most severe applicable category is Destructive. Execute · Medium fin_deepagent_cancel This tool terminates/cancels an active running process. Execute · High fin_deepagent_research_submit This tool triggers an external long-running computation task on a remote system. Write · High strategy_publish Publishing a strategy to a Hub server is fundamentally a Write operation—it creates or uploads data to a persistent remote location.

5 of OpenFinClaw CLI's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control OpenFinClaw CLI

PolicyLayer is an MCP gateway — it sits between your AI agents and OpenFinClaw CLI, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "fin_deepagent_threads": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "strategy_fork": {
    "limits": [
      {
        "counter": "strategy_fork_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "fin_deepagent_research_finalize": {
    "limits": [
      {
        "counter": "fin_deepagent_research_finalize_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register OpenFinClaw CLI — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON OPENFINCLAW CLI →

Free to start. No card required.

FULL CATALOGUE

All 21 OpenFinClaw CLI tools

DESTRUCTIVE 1 tools

Destructive fin_deepagent_threads Manage DeepAgent threads — list, create, get, or delete

EXECUTE 2 tools

Execute fin_deepagent_cancel Cancel a running DeepAgent run Execute fin_deepagent_research_submit Start a long-running DeepAgent research task (takes 3-10 min). Returns a taskId IMMEDIATELY.

WRITE 2 tools

Write strategy_fork Fork a public strategy from Hub to local directory Write strategy_publish Publish a strategy ZIP to Hub server (auto-runs backtest)

READ 16 tools

Read fin_deepagent_research_finalize Retrieve the full final text of a completed research run and clear local state. Read fin_deepagent_backtest_result Get the full backtest report for a given task (metrics / trades / equity curve) Read fin_deepagent_backtests List DeepAgent-generated backtest summaries (returns, sharpe, drawdown, etc.) Read fin_deepagent_download_package Download a strategy package ZIP to local disk (default: ~/.openfinclaw/deepagent-packages/) Read fin_deepagent_health Check DeepAgent service health (public, no API key required) Read fin_deepagent_messages Read messages in a DeepAgent thread Read fin_deepagent_package_meta Get strategy package metadata (parameters / template / validation) Read fin_deepagent_packages List strategy packages generated by DeepAgent Read fin_deepagent_research_poll Poll an in-progress research run. Blocks inside the MCP server for waitSeconds (default 20s, Read fin_deepagent_skills List DeepAgent analysis skills (~60 entries; public, no API key required) Read fin_deepagent_status List all active DeepAgent tasks in this MCP server, or get status of one task Read strategy_get_info Get strategy details from Hub Read strategy_leaderboard Query strategy leaderboard from Hub Read strategy_list_local List all local strategies (forked or created) Read strategy_validate Validate a strategy package directory (FEP v2.0) Read strategy_publish_verify Check publish and backtest status by submission or task ID

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about OpenFinClaw CLI

Can an AI agent delete data through the OpenFinClaw CLI MCP server? +

Yes. The OpenFinClaw CLI server exposes 1 destructive tools including fin_deepagent_threads. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through OpenFinClaw CLI? +

The OpenFinClaw CLI server has 2 write tools including strategy_fork, strategy_publish. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach OpenFinClaw CLI.

How many tools does the OpenFinClaw CLI MCP server expose? +

21 tools across 4 categories: Destructive, Financial, Read, Write. 16 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on OpenFinClaw CLI? +

Register the OpenFinClaw CLI MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every OpenFinClaw CLI tool call.

Deterministic rules across all 21 OpenFinClaw CLI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OPENFINCLAW CLI →

Free to start. No card required.

21 OpenFinClaw CLI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.