invoke_bedrock_prompt_stream

WHAT IT DOES

What invoke_bedrock_prompt_stream does on Bedrock Prompts MCP Server

AI agents invoke invoke_bedrock_prompt_stream to trigger actions in Bedrock Prompts MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why invoke_bedrock_prompt_stream needs a policy

This tool executes prompts against LLMs via AWS Bedrock, causing external API calls with side effects determined by prompt arguments. The ability to invoke multiple AI models with variable substitution means an agent could execute arbitrary prompts with unpredictable outcomes.

From the tool's definition Tool name contains 'invoke' and description states 'Invoke a Bedrock prompt' which triggers execution of an external AI service.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

invoke_bedrock_prompt_stream Rate-limited

invoke_bedrock_prompt_stream stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "invoke_bedrock_prompt_stream": {
      "limits": [
        {
          "counter": "invoke_bedrock_prompt_stream_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Bedrock Prompts MCP Server, so you can run agents against it safely.

FAQ

Questions about invoke_bedrock_prompt_stream

What does the invoke_bedrock_prompt_stream tool do? +

Invoke a Bedrock prompt with streaming response. Returns text chunks as they. It is categorised as a Execute tool in the Bedrock Prompts MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invoke_bedrock_prompt_stream? +

Register the Bedrock Prompts MCP Server MCP server in PolicyLayer and add a rule for invoke_bedrock_prompt_stream: 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 Bedrock Prompts MCP Server. Nothing to install.

What risk level is invoke_bedrock_prompt_stream? +

invoke_bedrock_prompt_stream is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit invoke_bedrock_prompt_stream? +

Yes. Add a rate_limit block to the invoke_bedrock_prompt_stream 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 invoke_bedrock_prompt_stream completely? +

Set action: deny in the PolicyLayer policy for invoke_bedrock_prompt_stream. 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 invoke_bedrock_prompt_stream? +

invoke_bedrock_prompt_stream is provided by the Bedrock Prompts MCP Server MCP server (mslangford/bedrock-prompts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.