Skip to main content
Glama

aw1-circuit-breaker-remote

aw1_execute_protected_tool

Deterministic AST deconstruction and Gate 7 runtime circuit breaker preventing rogue shell escapes, dynamic eval(), and covert lateral socket egress in autonomous LLM tool calls.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "tool_name": "<tool_name>",
      "payload": "<payload>"
    },
    "name": "aw1_execute_protected_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
payloadYesRaw serialized invocation arguments, commands, or python code
agent_idNoUnique cryptographic identifier of the proposing autonomous agentagent_planner
tool_nameYesThe target tool function name proposed by the agent

Output Schema

NameRequiredDescriptionDefault
statusYesArbitration outcome: PERMITTED, HALTED, or ISOLATED
attestation_idNoCryptographic TEE hardware receipt reference
execution_tokenNoSingle-use ephemeral token authorizing downstream dispatch

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / agent_id / description
      Added value: +"Unique cryptographic identifier of the proposing autonomous agent"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "attestation_id": {
      +      "description": "Cryptographic TEE hardware receipt reference",
      +      "type": "string"
      +    },
      +    "execution_token": {
      +      "description": "Single-use ephemeral token authorizing downstream dispatch",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "Arbitration outcome: PERMITTED, HALTED, or ISOLATED",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "status"
      +  ],
      +  "type": "object"
      +}
  2. Changed4 schema fields changed
    • changedInput schema / properties / agent_id / default
      Previous value: -"default_agent"New value: +"agent_planner"
    • removedInput schema / properties / agent_id / description
      Removed value: -"Unique identifier of the calling agent instance for rate-limiting and audit ledger attribution."
    • changedInput schema / properties / payload / description
      Previous value: -"The exact serialized command, arguments, or code string submitted for AST deconstruction and policy validation."New value: +"Raw serialized invocation arguments, commands, or python code"
    • changedInput schema / properties / tool_name / description
      Previous value: -"The canonical function or tool name the agent intends to dispatch (e.g., 'bash', 'write_file', 'network_socket')."New value: +"The target tool function name proposed by the agent"
  3. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
      +  "default": "default_agent",
      +  "description": "Unique identifier of the calling agent instance for rate-limiting and audit ledger attribution.",
      +  "type": "string"
      +}
    • changedInput schema / properties / payload / description
      Previous value: -"Serialized parameters or code payload"New value: +"The exact serialized command, arguments, or code string submitted for AST deconstruction and policy validation."
    • changedInput schema / properties / tool_name / description
      Previous value: -"Target tool name to execute"New value: +"The canonical function or tool name the agent intends to dispatch (e.g., 'bash', 'write_file', 'network_socket')."
  4. Changed3 schema fields changed
    • removedInput schema / properties / agent_id
      Removed value: -{
      -  "default": "agent_planner",
      -  "type": "string"
      -}
    • changedInput schema / properties / payload / description
      Previous value: -"Raw serialized invocation arguments, commands, or python code"New value: +"Serialized parameters or code payload"
    • changedInput schema / properties / tool_name / description
      Previous value: -"The target tool function name proposed by the agent"New value: +"Target tool name to execute"
  5. First observed

TDQS

C2.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false; the description adds real context by stating that payloads are statically inspected and that shell escapes, eval(), and socket egress are blocked. It does not say what happens when a payload is rejected, whether the target tool actually runs, or what side effects occur on success.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single sentence, but it is dense with undefined jargon ('Gate 7', 'AST deconstruction', 'lateral socket egress') and lacks a clear subject-verb statement of the action. Length is fine; clarity and structure are not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, but for a tool that runs arbitrary agent-proposed code the description omits rejection behavior, error semantics, and what the returned result represents. Too much of the operational contract is left unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all three parameters are already documented, and the description adds only the implication that 'payload' is parsed as code. It gives no guidance on serialization format, how tool_name is validated, or what agent_id affects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a noun phrase naming security mechanisms ('AST deconstruction', 'Gate 7 runtime circuit breaker') rather than a verb+resource statement of what the tool does. It never says it executes the proposed tool, so the actual action is only recoverable from the tool name itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, and no reference to the sibling aw1_verify_tee_attestation or any other alternative. An agent must infer from the name that this is the path for running a proposed tool call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources