EndpointLLMCompletionWithMCP
Python template · sinapsis_chatbots_base.templates.endpoint_llm_completion_mcp
Overview
Template for OpenAI-compatible endpoint chat completion with MCP tool support.
Capabilities
Capabilities: not setInstallation
Install the published package using pip or uv.
pip install sinapsis-chatbots-base==1.0.0uv pip install sinapsis-chatbots-base==1.0.0uv add sinapsis-chatbots-base==1.0.0Configuration
Effective fields from the inspector schema, including nested Pydantic model fields.
Optional
Default: null
Required
Default: null
Optional API key override. Falls back to `LLM_API_KEY`.
Optional
Default: null
Request timeout in seconds.
Optional
Default: 120
Base URL for the OpenAI-compatible endpoint.
Required
Default: null
Explicit model name. When `None`, the endpoint default is used.
Optional
Default: null
Additional headers to include in requests.
Optional
Default: null
Tool-choice directive for the endpoint request.
Optional
Default: "auto"
Optional
Default: null
Optional seed for reproducibility.
Optional
Default: null
Stop sequences.
Optional
Default: null
Optional
Default: null
Optional
Default: null
Maximum number of output tokens.
Optional
Default: 4096
Optional
Default: null
Extra provider-specific request arguments.
Optional
Default: null
Optional
Default: null
Output mode. Aliased to `type`.
Optional
Default: "text"
Optional schema used for structured JSON output. Aliased to `schema`.
Optional
Default: null
Required root property names.
Optional
Default: null
Root schema properties.
Optional
Default: null
Whether extra root-level fields are allowed.
Optional
Default: null
Presence penalty.
Optional
Default: null
Frequency penalty.
Optional
Default: null
Optional
Default: true
Maximum number of consecutive failed tool rounds before stopping.
Optional
Default: 3
Optional
Default: "</think>"
Whether tool descriptions should be appended to the system prompt.
Optional
Default: true
Optional
Default: "<think>"
Whether tool definitions should be sent through the endpoint payload.
Optional
Default: true
Configuration example
Example from the Python docstring:
agent:
name: time_mcp_client
templates:
- template_name: InputTemplate
class_name: InputTemplate
attributes: {}
- template_name: EndpointLLMCompletionWithMCP
class_name: EndpointLLMCompletionWithMCP
template_input: InputTemplate
attributes:
init_args:
base_url: "http://localhost:8000/v1"
llm_model_name: "Qwen/Qwen3-8B"
completion_args:
max_tokens: 2048
temperature: 0.2Show schema-based configuration skeleton
templates:
- template_name: "EndpointLLMCompletionWithMCP"
class_name: "EndpointLLMCompletionWithMCP"
attributes:
init_args:
api_key: null
timeout: 120
base_url: "<required>"
llm_model_name: null
default_headers: null
tool_choice: "auto"
completion_args:
seed: null
stop: null
top_k: null
top_p: null
max_tokens: 4096
temperature: null
additional_args: null
response_format:
type_: "text"
schema_:
required: null
properties: null
additional_properties: null
presence_penalty: null
frequency_penalty: null
cleanup_response: true
max_tool_retries: 3
reasoning_end_tag: "</think>"
add_tool_to_prompt: true
reasoning_start_tag: "<think>"
send_tools_in_payload: true
Inheritance
sinapsis_chatbots_base.templates.endpoint_llm_completion.EndpointLLMCompletionEnvironment variables
Environment definitions belong to their canonical Python modules.
No directly related environment variables listed.