// SCAN REPORT

APIClaw

24 tools. 8 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

8 can modify or destroy data

16 read-only

24 tools total

Community server · catalogue entry verified 12/06/2026

How to control APIClaw ↓

TOOL MAP

What APIClaw exposes to your agents

Read (16) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous APIClaw tools

Financial · Critical setup_metered_billing This tool commits a financial obligation by creating a recurring billing subscription. Execute · High call_api This is Execute rather than Write because the tool executes arbitrary external API calls whose effects span create, read, update, delete, or trigger external systems—all determined by runtime arguments. Execute · High capability This tool executes arbitrary jobs via semantic capability matching. Execute · High start_mission This tool triggers execution of a mission/orchestration on the APIClaw platform.

8 of APIClaw's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control APIClaw

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

Block financial tools by default

{
  "setup_metered_billing": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Rate limit write operations

{
  "verify_code": {
    "limits": [
      {
        "counter": "verify_code_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "apiclaw_help": {
    "limits": [
      {
        "counter": "apiclaw_help_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 APIClaw — 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 APICLAW →

Free to start. No card required.

FULL CATALOGUE

All 24 APIClaw tools

FINANCIAL 1 tools

Financial setup_metered_billing Set up pay-per-call billing. Creates a subscription that charges $0.002 per API call at end of month.

EXECUTE 4 tools

Execute call_api Execute a callable API through APIClaw Execute capability Run a job-to-be-done by capability name (currency_convert, web_search, tts, transcribe, scrape, etc.). APIClaw Execute start_mission Start a Control Plane mission — a structured, observable orchestration that runs on APIClaw Execute resume_chain Resume a paused or partially-executed chain by id.

WRITE 3 tools

Write verify_code Verify the 6-digit code sent to your email after register_owner. This completes registration and activates you Write register_owner LEGACY auth path (kept for back-compat). The canonical agent-native flow is Write remind_owner Send a reminder email to verify workspace ownership (if verification is pending).

READ 16 tools

Read apiclaw_help Get help and a tour of APIClaw Read check_balance Check workspace balance, tier, and remaining calls in this billing period. Read check_workspace_status Health check for the current workspace (auth state, tier, gating, blockers). Read discover_apis Search APIClaw Read discover_missions Search mission templates by natural-language query. Returns ranked templates with slug, version, title, descri Read estimate_cost Estimate the cost of a given number of API calls for the current workspace. Read get_api_details Full specs, pricing, auth, and usage examples for a specific API. Read get_chain_status Check the status of an async chain execution (returned from call_api with async: true). Read get_usage_summary Summary of recent workspace usage (calls, providers, cost) for the current billing period. Read list_capabilities List capability shortcuts (e.g. Read list_connected List all managed providers ready for instant calls (no key required). Read list_mission_templates List available Control Plane mission templates and the parameters each accepts. Read list_missions List recent missions in the current workspace (most recent first). Read list_models List every LLM the workspace can call through APIClaw — Anthropic, OpenAI, xAI/Grok, Groq, Mistral, Together, Read mission_status Check status, audit events, cost, and final result for a mission started via start_mission.

EXPLORE

Related servers

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

FAQ

Questions about APIClaw

Can an AI agent move money through the APIClaw MCP server? +

Yes. The APIClaw server exposes 1 financial tools including setup_metered_billing. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

How do I prevent bulk modifications through APIClaw? +

The APIClaw server has 3 write tools including verify_code, register_owner, remind_owner. 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 APIClaw.

How many tools does the APIClaw MCP server expose? +

24 tools across 3 categories: Execute, Read, Write. 16 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on APIClaw? +

Register the APIClaw 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 APIClaw tool call.

Deterministic rules across all 24 APIClaw tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON APICLAW →

Free to start. No card required.

24 APIClaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.