Skip to main content
Glama
deepset-ai

deepset-mcp

Official
by deepset-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

create_deployment

Create a new AI Gateway deployment, optionally linked to a pipeline, with configurable mode, sizing, and replica settings for managed or serverless execution.

Instructions

Creates a new deployment (AI Gateway), optionally linked to a pipeline.

A deployment created without an origin_pipeline_id has no active revision until you call create_deployment_revision and activate_deployment_revision. Default service sizing follows Development unless explicit sizing fields are provided. :param name: Name of the deployment. :param description: Optional description. :param group_label: Optional label used to group related deployments. :param origin_pipeline_id: ID of the platform pipeline to link, if any. :param deployment_mode: Execution mode, "MANAGED" or "SERVERLESS" (default "MANAGED"). :param service_level: Sizing tier, "PRODUCTION", "DEVELOPMENT", or "CUSTOM" (default "DEVELOPMENT"). :param idle_timeout_in_seconds: Seconds of inactivity before scaling down. :param min_query_replica_count: Minimum number of query replicas. :param max_query_replica_count: Maximum number of query replicas. :param max_index_replica_count: Maximum number of index replicas. :param cpu_request: Requested CPU per replica. :param cpu_limit: CPU limit per replica. :param memory_request: Requested memory per replica. :param memory_limit: Memory limit per replica. :param gpu_limit_gigabyte: GPU memory limit in gigabytes. :returns: The created deployment or error message.

All parameters accept object references in the form @obj_id or @obj_id.path.to.value.

Examples::

# Direct call with values
create_deployment(data={'key': 'value'}, threshold=10)

# Call with references
create_deployment(data='@obj_123', threshold='@obj_456.config.threshold')

# Mixed call
create_deployment(data='@obj_123.items', threshold=10)The output is automatically stored and can be referenced in other functions.

Returns a formatted preview with an object ID (e.g., @obj_123). Use the object store tools in combination with the object ID to view nested properties of the object. Use the returned object ID to pass this result to other functions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
cpu_limitNo
cpu_requestNo
descriptionNo
group_labelNo
memory_limitNo
service_levelNoDEVELOPMENT
memory_requestNo
deployment_modeNoMANAGED
gpu_limit_gigabyteNo
origin_pipeline_idNo
idle_timeout_in_secondsNo
max_index_replica_countNo
max_query_replica_countNo
min_query_replica_countNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.27

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses default behavior (sizing defaults to DEVELOPMENT unless explicit sizing fields are given), the post-creation state (no active revision without a pipeline), and that output is auto-stored and returned as an object ID. It says nothing about permissions/auth requirements, provisioning side effects, or costs, which are meaningful gaps for a create-a-resource operation.

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

Conciseness3/5

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

Purpose and the critical 'no active revision' caveat are front-loaded, and the param reference is justified by 15 undocumented params. However, the Examples block is generic boilerplate that references 'data' and 'threshold' – parameters that do not exist on create_deployment – which adds noise and potential confusion rather than value.

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

Completeness4/5

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

For a 15-parameter mutation tool with no annotations and no output schema, the description is fairly complete: it covers parameter meaning, defaults, the revision workflow dependency, and the return/preview behavior (object ID usable with object store tools). It omits auth/permission prerequisites and any description of the created deployment's fields, but an agent has enough to invoke it correctly.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate, and it does: a full :param list documents all 15 parameters with semantics and defaults (e.g., idle_timeout_in_seconds as 'Seconds of inactivity before scaling down', the MANAGED/SERVERLESS and PRODUCTION/DEVELOPMENT/CUSTOM enums, and the @obj_id reference syntax). Some entries are near-tautological (e.g., 'Name of the deployment', 'Maximum number of index replicas'), keeping it out of the top score.

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

Purpose4/5

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

The opening sentence gives a specific verb and resource ('Creates a new deployment (AI Gateway)') plus the scoping condition that it is optionally linked to a pipeline. An agent can distinguish this from siblings like create_deployment_revision, update_deployment, and deploy_pipeline. It stops short of explicitly naming which sibling to use in which situation.

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

Usage Guidelines4/5

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

The description explains the key branch: without an origin_pipeline_id the deployment has no active revision until create_deployment_revision and activate_deployment_revision are called, which effectively routes the agent to the follow-up tools. It lacks explicit exclusions or guidance on when not to use create_deployment, but the workflow context is clear.

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

Deploy Server

Other Tools