Python MCP reference

tool MCPstable

`call_read_tools_batch`

call_read_tools_batch( on_error?: "stop" | "continue", operations: Array<object>, )

tool [source]¶

Call several inspect tools serially and return per-tool results.

Use when one agent turn needs several observations. Each nested call still goes through FastMCP validation and this server’s middleware. Only inspect tools are accepted; anything that changes tmux state is refused, whatever this server has enabled.

This wrapper aggregates authority under its own name: a client rule keyed on a nested tool’s name does not fire for a call made through it. Read it as authority to invoke any inspect tool.

MCP request method: tools/call Send call_read_tools_batch as the tool name, with the arguments below.

Arguments#

on_error? = "stop" ("stop" | "continue") #
operations (Array<object>) #
- Items (object) #
  
  One nested MCP tool call for a batch wrapper.
  - arguments? (object) #
    
    Arguments for the nested tool call.
  - tool (string) #
    
    Registered MCP tool name to call.
  No other properties are accepted.

No other arguments are accepted.

Result#

Returns object

failed (integer) #

Number of nested tool calls that failed.
response_truncated? = false (boolean) #

True when nested result payloads were elided to keep the batch response under the server response cap.
response_truncated_bytes? = 0 (integer) #

Approximate serialized bytes removed from nested result payloads.
results? (Array<object>) #

Per-operation results in attempted order.
- Items (object) #
  
  Per-operation result from a generic MCP tool batch.
  - content? (Array<object>) #
    
    MCP content blocks returned by the nested tool.
    - Items (object) #
  - elapsed_seconds (number) #
    
    Time spent on this operation.
  - error? = null (string | null) #
    
    Error message for this operation, if it failed.
  - index (integer) #
    
    Zero-based index in the submitted operation list.
  - meta? = null (object | null) #
    
    Runtime metadata returned by the nested tool, if any.
    
    Matches one or more variants.
    - Variant 1 (object) #
  - structured_content? = null (object | null) #
    
    Structured content returned by the nested tool, if any.
    
    Matches one or more variants.
    - Variant 1 (object) #
  - success (boolean) #
    
    True when this nested tool call succeeded.
  - tool (string) #
    
    Nested tool name that was attempted.
stopped_at? = null (integer | null) #

Index where processing stopped because on_error=‘stop’, or None when all operations were attempted.
succeeded (integer) #

Number of nested tool calls that succeeded.

Annotations#

destructiveHint: true
idempotentHint: false
openWorldHint: true
readOnlyHint: false

Protocol data#

Use the complete advertised contract for validation and client integration.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "on_error": {
      "default": "stop",
      "enum": [
        "stop",
        "continue"
      ],
      "type": "string"
    },
    "operations": {
      "items": {
        "additionalProperties": false,
        "description": "One nested MCP tool call for a batch wrapper.",
        "properties": {
          "arguments": {
            "additionalProperties": true,
            "description": "Arguments for the nested tool call.",
            "type": "object"
          },
          "tool": {
            "description": "Registered MCP tool name to call.",
            "type": "string"
          }
        },
        "required": [
          "tool"
        ],
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "operations"
  ],
  "type": "object"
}

Output schema

{
  "description": "Structured result for a serial batch of MCP tool calls.",
  "properties": {
    "failed": {
      "description": "Number of nested tool calls that failed.",
      "type": "integer"
    },
    "response_truncated": {
      "default": false,
      "description": "True when nested result payloads were elided to keep the batch response under the server response cap.",
      "type": "boolean"
    },
    "response_truncated_bytes": {
      "default": 0,
      "description": "Approximate serialized bytes removed from nested result payloads.",
      "type": "integer"
    },
    "results": {
      "description": "Per-operation results in attempted order.",
      "items": {
        "description": "Per-operation result from a generic MCP tool batch.",
        "properties": {
          "content": {
            "description": "MCP content blocks returned by the nested tool.",
            "items": {
              "additionalProperties": true,
              "type": "object"
            },
            "type": "array"
          },
          "elapsed_seconds": {
            "description": "Time spent on this operation.",
            "type": "number"
          },
          "error": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Error message for this operation, if it failed."
          },
          "index": {
            "description": "Zero-based index in the submitted operation list.",
            "type": "integer"
          },
          "meta": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Runtime metadata returned by the nested tool, if any."
          },
          "structured_content": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "Structured content returned by the nested tool, if any."
          },
          "success": {
            "description": "True when this nested tool call succeeded.",
            "type": "boolean"
          },
          "tool": {
            "description": "Nested tool name that was attempted.",
            "type": "string"
          }
        },
        "required": [
          "index",
          "tool",
          "success",
          "elapsed_seconds"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "stopped_at": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Index where processing stopped because on_error='stop', or None when all operations were attempted."
    },
    "succeeded": {
      "description": "Number of nested tool calls that succeeded.",
      "type": "integer"
    }
  },
  "required": [
    "succeeded",
    "failed"
  ],
  "type": "object"
}

Scripting & web

Compiled & native

JVM

.NET

tmux

`call_read_tools_batch`

Arguments#

Result#

Annotations#

Protocol data#