raposa

endpoint

https://dcescrypt.com/api/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is raposa live?

Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.

Is raposa free to use?

No — it asks for a key or a login before it will serve.

What tools does raposa have?

3 tools: create_approval, request_human_approval, get_approval.

Is raposa safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_approval auth-required 1h ago

  Read an approval by id. Look at `approved` — it is true only when a human approved.

  mcp-tool

  123456789101112

  {
    "type": "object",
    "required": [
      "approval_id"
    ],
    "properties": {
      "approval_id": {
        "type": "string",
        "description": "Approval id returned by create_approval or request_human_approval"
      }
    }
  }

  arguments 12 lines copy
• create_approval unknown never probed

  Create an approval request and return its id immediately (no waiting). Use with a webhook_url, or poll with get_approval. risk: low | medium | high.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940

  {
    "type": "object",
    "required": [
      "action",
      "context",
      "risk"
    ],
    "properties": {
      "risk": {
        "enum": [
          "low",
          "medium",
          "high"
        ],
        "type": "string",
        "description": "How much damage a wrong decision does: low | medium | high"
      },
      "action": {
        "type": "string",
        "description": "What the agent wants to do, one line (max 200 chars)"
      },
      "context": {
        "type": "string",
        "description": "Why, for whom, amounts, ids — what the human needs to decide (max 4000 chars)"
      },
      "webhook_url": {
        "type": "string",
        "description": "Where to POST the signed decision"
      },
      "requested_by": {
        "type": "string",
        "default": "mcp-agent",
        "description": "Name of the agent or workflow"
      },
      "expires_in_sec": {
        "type": "integer",
        "description": "How long the request stays open (default 86400)"
      }
    }
  }

  arguments 40 lines copy
• request_human_approval unknown never probed

  Ask an authorised human to approve an action and wait for the answer (up to wait_sec, max 50). Returns {approved: bool, status, decided_by, ...}. Proceed ONLY if approved is true — a timeout, an expiry or a rejection means do not proceed. On timeout the request stays open: check later with get_approval. risk: low | medium | high.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243

  {
    "type": "object",
    "required": [
      "action",
      "context",
      "risk"
    ],
    "properties": {
      "risk": {
        "enum": [
          "low",
          "medium",
          "high"
        ],
        "type": "string",
        "description": "How much damage a wrong decision does: low | medium | high"
      },
      "action": {
        "type": "string",
        "description": "What the agent wants to do, one line (max 200 chars)"
      },
      "context": {
        "type": "string",
        "description": "Why, for whom, amounts, ids — what the human needs to decide (max 4000 chars)"
      },
      "wait_sec": {
        "type": "integer",
        "default": 50,
        "maximum": 50,
        "minimum": 0,
        "description": "Seconds to wait for a decision (0–50)"
      },
      "requested_by": {
        "type": "string",
        "default": "mcp-agent",
        "description": "Name of the agent or workflow"
      },
      "expires_in_sec": {
        "type": "integer",
        "description": "How long the request stays open (default 86400)"
      }
    }
  }

  arguments 43 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.