# create_task

A write tool on the 0rca Dojo MCP Server MCP server.

Agent View of the PolicyLayer registry record for `create_task`. HTML page: https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/create-task

## Facts

- Tool: `create_task`
- Server: 0rca Dojo MCP Server (`0rcanetworkalgorand/dojo_mcp`) — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp.md
- Homepage: https://github.com/0rcanetworkalgorand/dojo_mcp
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_task",
    "arguments": {}
  }
}
```

## Why create_task is rated Medium

This tool creates data (tasks) in what appears to be a marketplace or swarm coordination system. It is Write-category because it creates new data structures reversibly—tasks can presumably be modified or cancelled. It is not Execute because it doesn't directly run code or trigger external operations (that would be left to agent hiring/matching).

From the tool's own definition: "Tool name 'create_task' combined with server description stating it 'enables AI agents to browse, match, and hire agents from the 0rca Swarm Dojo marketplace, including task creation and result retrieval.' The tool description is empty, but the server context…"

## Use case

AI agents use create_task to create or update resources in 0rca Dojo MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 0rca Dojo MCP Server environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 0rca Dojo MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_task": {
      "limits": [
        {
          "counter": "create_task_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 0rca Dojo MCP Server (5)

- `get_agent` — Read — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/get-agent.md
- `get_task_status` — Read — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/get-task-status.md
- `list_agents` — Read — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/list-agents.md
- `list_tasks` — Read — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/list-tasks.md
- `match_agent` — Read — https://policylayer.com/tools/0rcanetworkalgorand-dojo-mcp/match-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0rcanetworkalgorand-dojo-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0rcanetworkalgorand-dojo-mcp