add_deployment
Add a new deployment with custom configuration in the Enkrypt AI MCP Server, specifying input and output guardrails policies to manage AI safety and detection rules.
Instructions
Add a new deployment using the provided configuration.
Args: deployment_config: A dictionary containing the deployment configuration details.
Example Usage:
{
"deployment_config": {
sample_deployment_config = {
"name": deployment_name,
"model_saved_name": model_saved_name,
"input_guardrails_policy": {
"policy_name": policy_name,
"enabled": True,
"additional_config": {
"pii_redaction": False #Add these if any additional detectors than that in the policy are needed
},
"block": [
"injection_attack", # Could be any of the active detectors (Ask user if they want to block)
"policy_violation"
]
},
"output_guardrails_policy": {
"policy_name": policy_name,
"enabled": False,
"additional_config": {
"hallucination": False, #Add these if any additional detectors than that in the policy are needed
"adherence": False,
"relevancy": False
},
"block": [
"nsfw" # Could be any of the active detectors (Ask user if they want to block)
]
},
}
}
Always ask user if they want to block any of the detectors in the policy for both input and output. (if you dont know what detectors are present in the policy, you can use the get_guardrails_policy tool) Returns: A dictionary containing the response message and details of the added deployment.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| deployment_config | Yes |
Implementation Reference
- src/mcp_server.py:831-880 (handler)The handler function for the 'add_deployment' MCP tool. It is decorated with @mcp.tool() for registration and calls the deployment_client to add a deployment based on the provided config, returning the response as a dictionary. The docstring provides detailed input schema examples.@mcp.tool() def add_deployment(deployment_config: Dict[str, Any]) -> Dict[str, Any]: """ Add a new deployment using the provided configuration. Args: deployment_config: A dictionary containing the deployment configuration details. Example Usage: { "deployment_config": { sample_deployment_config = { "name": deployment_name, "model_saved_name": model_saved_name, "input_guardrails_policy": { "policy_name": policy_name, "enabled": True, "additional_config": { "pii_redaction": False #Add these if any additional detectors than that in the policy are needed }, "block": [ "injection_attack", # Could be any of the active detectors (Ask user if they want to block) "policy_violation" ] }, "output_guardrails_policy": { "policy_name": policy_name, "enabled": False, "additional_config": { "hallucination": False, #Add these if any additional detectors than that in the policy are needed "adherence": False, "relevancy": False }, "block": [ "nsfw" # Could be any of the active detectors (Ask user if they want to block) ] }, } } Always ask user if they want to block any of the detectors in the policy for both input and output. (if you dont know what detectors are present in the policy, you can use the get_guardrails_policy tool) Returns: A dictionary containing the response message and details of the added deployment. """ # Add the deployment using the provided configuration add_deployment_response = deployment_client.add_deployment(deployment_config) # Return the response as a dictionary return add_deployment_response.to_dict()