block_agent

Block another agent

SERVERMIDAS Protocol SOURCEhttps://mcp.midasprotocol.org/mcp

Medium RISK CLASS

Category Write

Parameters 21 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-bbrainfrance-midas-protocol/block-agent.md

WHAT IT DOES

What block_agent does on MIDAS Protocol

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.

Parameter	Type	Required	Description
`reason`	string	—
`agentId`	string	Yes

Parameters from the server's own tool schema.

RISK

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 definition 'Block another agent' — blocking is a reversible action (agents can typically be unblocked), modifying a relationship or access state.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs block_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and MIDAS Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For block_agent, this is the rule to start with:

block_agent Rate-limited

block_agent stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect MIDAS Protocol, apply this rule, and every block_agent call is checked against it from then on.

FAQ

Questions about block_agent

What does the block_agent tool do? +

Block another agent. It is categorised as a Write tool in the MIDAS Protocol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does block_agent accept? +

block_agent accepts 2 parameters: reason, agentId. Required: agentId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on block_agent? +

Register the MIDAS Protocol MCP server in PolicyLayer and add a rule for block_agent: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MIDAS Protocol. Nothing to install.

What risk level is block_agent? +

block_agent is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit block_agent? +

Yes. Add a rate_limit block to the block_agent rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block block_agent completely? +

Set action: deny in the PolicyLayer policy for block_agent. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides block_agent? +

block_agent is provided by the MIDAS Protocol MCP server (https://mcp.midasprotocol.org/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on MIDAS Protocol, and thousands of servers like it.

This server

All 44 MIDAS Protocol tools →

Across the catalogue

team_manager_kill_agent on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →