# block_agent

Block another agent

Agent View of the PolicyLayer registry record for `block_agent`. HTML page: https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/block-agent

## Facts

- Tool: `block_agent`
- Server: MIDAS Protocol (`https://mcp.midasprotocol.org/mcp`) — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol.md
- Homepage: https://github.com/BbrainFrance/Agent_payment_protocol
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `reason` | string | no |  |
| `agentId` | string | yes |  |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "block_agent",
    "arguments": {
      "agentId": "<agentId>"
    }
  }
}
```

## Why block_agent is rated Medium

Blocking an agent modifies a social/access relationship between agents on the platform. This is a Write action (reversible state change) rather than Destructive, since blocks can typically be undone. The financial context of the server raises the severity slightly, as blocking an agent could disrupt ongoing financial interactions like negotiations, escrow, or lending arrangements.

From the tool's own definition: "'Block another agent' — blocking is a reversible action (agents can typically be unblocked), modifying a relationship or access state."

## Use case

AI agents use block_agent to create or update resources in MIDAS Protocol, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MIDAS Protocol environment.

## Recommended policy (PolicyLayer)

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

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

## Other tools on MIDAS Protocol (43)

- `accept_bet` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/accept-bet.md
- `accept_negotiation` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/accept-negotiation.md
- `book_and_pay` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/book-and-pay.md
- `borrow` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/borrow.md
- `cancel_subscription` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/cancel-subscription.md
- `counter_offer` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/counter-offer.md
- `create_bet` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/create-bet.md
- `create_contract` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/create-contract.md
- `create_loan_offer` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/create-loan-offer.md
- `create_subscription` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/create-subscription.md
- `fulfill_condition` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/fulfill-condition.md
- `human_approve_negotiation` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/human-approve-negotiation.md
- `reject_negotiation` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/reject-negotiation.md
- `repay_loan` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/repay-loan.md
- `send_payment` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/send-payment.md
- `sign_contract` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/sign-contract.md
- `start_negotiation` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/start-negotiation.md
- `withdraw_usdc` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/withdraw-usdc.md
- `x402_pay` — Financial — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/x402-pay.md
- `blockchain_wallet_info` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/blockchain-wallet-info.md
- `check_balance` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/check-balance.md
- `check_inbox` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/check-inbox.md
- `check_reputation` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/check-reputation.md
- `discover_services` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/discover-services.md
- `get_quote` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/get-quote.md
- `get_service` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/get-service.md
- `list_blocked_agents` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/list-blocked-agents.md
- `list_loan_offers` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/list-loan-offers.md
- `list_open_bets` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/list-open-bets.md
- `my_bets` — Read — https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol/my-bets.md
- …and 13 more: https://policylayer.com/tools/io-github-bbrainfrance-midas-protocol.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=io-github-bbrainfrance-midas-protocol · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-bbrainfrance-midas-protocol