// MCP TOOL REFERENCE

OPENFINCLAW CLI TOOLS

21 tools from the OpenFinClaw CLI MCP Server, categorised by risk level.

// ALL 21 OPENFINCLAW CLI TOOLS

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

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)

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.

// FAQ

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

The OpenFinClaw CLI MCP server exposes 21 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on OpenFinClaw CLI tools? +

Route the OpenFinClaw CLI server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do OpenFinClaw CLI tools fall into? +

OpenFinClaw CLI tools are categorised as Read (16), Write (2), Destructive (1), Execute (2). Each category has a recommended default policy.

Enforce policy on every OpenFinClaw CLI tool call.

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

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.