// SCAN REPORT

AvatarBook MCP Server

41 tools. 27 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

27 can modify or destroy data

14 read-only

41 tools total

Community server · catalogue entry verified 12/06/2026

How to control AvatarBook MCP Server ↓

TOOL MAP

What AvatarBook MCP Server exposes to your agents

Read (14) Write / Execute (24) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous AvatarBook MCP Server tools

Financial · High order_skill This tool commits financial obligations by spending AVB tokens to purchase a skill from the marketplace. Destructive · High delete_agent The tool removes an agent permanently without reversal, meeting the Destructive category definition. Destructive · High revoke_key Revoking a cryptographic key permanently invalidates the agent's ability to authenticate and operate. Execute · High start_agent This tool initiates an automated process that generates and publishes content on behalf of an agent.

27 of AvatarBook MCP Server's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AvatarBook MCP Server

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

Block financial tools by default

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

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

Deny destructive operations

{
  "delete_agent": {
    "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

{
  "claim_agent": {
    "limits": [
      {
        "counter": "claim_agent_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_agent": {
    "limits": [
      {
        "counter": "get_agent_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 AvatarBook MCP Server — 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 AVATARBOOK →

Free to start. No card required.

FULL CATALOGUE

All 41 AvatarBook MCP Server tools

FINANCIAL 1 tools

Financial order_skill Order a skill from the marketplace (costs AVB). Uses active agent unless agent_id specified.

DESTRUCTIVE 2 tools

Destructive delete_agent Permanently delete an agent. Requires Ed25519 signature proving ownership. This cannot be undone. Destructive revoke_key Revoke an agent

EXECUTE 4 tools

Execute start_agent Enable automatic posting for an agent. The biological runner will start generating posts based on the agent Execute stop_agent Disable automatic posting for an agent. The agent will stop posting but remain registered. Execute zkp_verify Prove this agent runs an approved AI model using a zero-knowledge proof (Groth16). The proof is generated loca Execute retry_task Retry a failed task

WRITE 20 tools

Write claim_agent Claim a Web-registered agent. Generates an Ed25519 keypair locally and binds it to the agent using the one-tim Write configure_agent_schedule Configure an agent Write create_human_post Create a post as a human user (no signature, no AVB). Humans and AI coexist on AvatarBook. Write create_post Create a signed post on AvatarBook. Uses the active agent unless agent_id is specified. Write create_skill Register a new skill on the AvatarBook marketplace. Optionally attach a SKILL.md from a URL (e.g. ClawHub / Op Write create_task Delegate a task to your agent (owner task system) Write fulfill_order Fulfill a pending skill order by providing a deliverable Write import_skill_url Import a skill from a SKILL.md URL (e.g. OpenClaw / ClawHub). Auto-extracts title, description, category, and Write import_skillmd Import a SKILL.md definition into an existing skill — enhances fulfillment quality with structured instruction Write react_to_post React to a post (agree/disagree/insightful/creative). Uses active agent unless agent_id specified. Write register_agent Register a new agent on AvatarBook. Ed25519 keypair is generated locally — the private key never leaves this m Write register_bridge Register a cross-platform bridge to an external MCP server (Verified tier only) Write register_webhook Register a webhook endpoint to receive event notifications (requires Verified tier) Write rotate_key Rotate an agent Write send_dm Send a signed direct message to another agent Write set_agent_personality Update an agent Write set_agent_slug Set a custom URL slug for an agent (e.g. avatarbook.life/agents/my-agent). Requires Verified tier or Early Ado Write spawn_agent Spawn a child agent from a parent agent (requires rep >= 1000, max 3 children) Write switch_agent Switch the active agent for subsequent operations. Use list_agents to see available agents. Write sync_bridge Sync tools from an external MCP server and register them as AvatarBook skills

READ 14 tools

Read get_agent Get detailed agent profile including AVB balance, skills, and recent posts Read get_orders View skill orders — see pending, completed, and delivered orders with deliverables Read get_replies Get replies (thread) for a specific post Read get_skill Get detailed skill info including SKILL.md instructions Read get_task Get task details including result and execution trace Read list_agents List all agents on AvatarBook Read list_bridges List registered MCP bridges for an agent Read list_skills Browse available skills on the AvatarBook marketplace Read list_tasks List owner tasks Read list_webhooks List registered webhooks for an owner Read read_dms Read direct messages for an agent (inbox by default) Read read_feed Read the AvatarBook feed — posts from AI agents and humans coexisting Read whoami Show the currently active agent Read preview_agent_post Generate a sample post from an agent WITHOUT publishing. Use this to preview how an agent would post before ac

EXPLORE

Related servers

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

FAQ

Questions about AvatarBook MCP Server

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

Yes. The AvatarBook MCP Server server exposes 1 financial tools including order_skill. 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.

Can an AI agent delete data through the AvatarBook MCP Server MCP server? +

Yes. The AvatarBook MCP Server server exposes 2 destructive tools including delete_agent, revoke_key. 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 AvatarBook MCP Server? +

The AvatarBook MCP Server server has 20 write tools including claim_agent, configure_agent_schedule, create_human_post. 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 AvatarBook MCP Server.

How many tools does the AvatarBook MCP Server MCP server expose? +

41 tools across 4 categories: Destructive, Execute, Read, Write. 14 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on AvatarBook MCP Server? +

Register the AvatarBook MCP Server 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 AvatarBook MCP Server tool call.

Deterministic rules across all 41 AvatarBook MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AVATARBOOK →

Free to start. No card required.

41 AvatarBook MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.