Skip to main content
Glama
RawTree MCP Server

RawTree MCP Server

Official
by rawtreedb

Create Cluster

create-cluster

Provisions a RawTree dedicated cluster in an organization with configurable replicas, vertical autoscaling, and optional customer-owned S3 storage; provisioning continues asynchronously.

Instructions

Purpose: Provision a new RawTree dedicated cluster in an organization.

Returns: The newly created cluster, including its ID, lifecycle status, and initial resources. Provisioning continues asynchronously after the request is accepted; use get-cluster to check progress.

Behavior: The cluster starts at minimumSize and can vertically autoscale per replica up to maximumSize. The replica count remains fixed. s3Storage is optional: omit it to use RawTree-managed storage. When provided, it configures customer-owned data and backup destinations through a customer IAM role. Destination paths are optional; data and backups (each with a bucket), plus roleArn are required inside s3Storage. s3StorageAccess contains the immutable externalId and resourceTag for this cluster's S3 storage access. The API generates omitted values independently using secure UUIDs, but requires an explicit s3StorageAccess.externalId for custom S3 matching the customer IAM trust policy. The MCP client forwards optional identity values without generating them. Tag eligible customer buckets and IAM roles with rawtree.com/cluster=. Database operations reuse this saved identity automatically.

Auth: The RawTree API requires a user access token with organization admin access. Authorization is enforced by the API.

Safety: When selecting a region, first call list-cluster-regions and use the same regionId for list-cluster-sizes, verify-cluster-s3-access and create-cluster. You MUST first call list-cluster-sizes, then confirm the exact organization, region, name, replica count, minimum per-replica size, maximum per-replica size, vertical autoscaling behavior, and idle timeout with the user. If idleTimeoutMinutes is omitted, explain that the server default will apply. For one replica, warn that the cluster has no redundancy. If s3Storage is provided, first call verify-cluster-s3-access with the identical configuration and confirm the data and backup buckets, optional paths, role ARN, and External ID. Pass the same s3StorageAccess.externalId to verification and creation. Never reuse a successful verification after changing s3StorageAccess.externalId or any s3Storage field. Confirm any explicitly supplied identity values with the user; generated values are returned with the cluster.

Reliability: This operation is not idempotent. If the response is ambiguous, call list-clusters to reconcile by organization and name before retrying.

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": {
      "organization": "<organization>",
      "regionId": "<regionId>",
      "name": "<name>",
      "replicas": "<replicas>",
      "minimumSize": "<minimumSize>",
      "maximumSize": "<maximumSize>"
    },
    "name": "create-cluster"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesURL-friendly cluster name using letters, numbers, '_' or '-'.
regionIdYesRegion ID returned by list-cluster-regions. Use the same region for sizes, S3 verification and creation.
replicasYesNumber of cluster replicas.
s3StorageNoOptional customer-owned S3 configuration. Omit to use RawTree-managed storage. Verify the identical configuration with verify-cluster-s3-access before creation.
maximumSizeYesMaximum vertical autoscaling size returned by list-cluster-sizes. Must be at or above minimumSize in the returned catalog.
minimumSizeYesInitial and minimum vertical autoscaling size returned by list-cluster-sizes.
organizationYesOrganization in which to create the cluster.
s3StorageAccessNoCreation-only S3 storage identity overrides. Omit to let the API generate values. Custom storage requires externalId matching verification.
idleTimeoutMinutesNoMinutes of inactivity before automatically pausing. Use 0 to disable idling. Omit to use the server default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.5
    • changedInput schema / properties / regionId / description
      Previous value: -"Region ID returned by list-regions. Use the same region for sizes, S3 verification and creation. Omit for the default backend."New value: +"Region ID returned by list-cluster-regions. Use the same region for sizes, S3 verification and creation."
    • changedInput schema / required
      Previous value: -[
      -  "organization",
      -  "name",
      -  "replicas",
      -  "minimumSize",
      -  "maximumSize"
      -]New value: +[
      +  "organization",
      +  "regionId",
      +  "name",
      +  "replicas",
      +  "minimumSize",
      +  "maximumSize"
      +]
  2. Changed16 schema fields changedv0.4.2
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / databaseS3Access
      Removed value: -{
      -  "description": "Optional independent per-database S3 capability. It may be supplied without s3Storage. Apply the databaseBucketTag to each customer-owned database bucket; if s3Storage is also supplied, externalId must match.",
      -  "properties": {
      -    "databaseBucketTag": {
      -      "description": "Lowercase tag value applied to every customer-owned database bucket as rawtree.com/cluster=<value>.",
      -      "maxLength": 256,
      -      "minLength": 1,
      -      "pattern": "^[a-z0-9][a-z0-9-]*$",
      -      "type": "string"
      -    },
      -    "externalId": {
      -      "description": "External ID used by customer IAM role trust policies. It must exactly match the cluster S3 storage External ID when both are configured.",
      -      "maxLength": 1224,
      -      "minLength": 2,
      -      "pattern": "^[A-Za-z0-9_+=,.@:/-]+$",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "externalId",
      -    "databaseBucketTag"
      -  ],
      -  "type": "object"
      -}
    • addedInput schema / properties / regionId
      Added value: +{
      +  "description": "Region ID returned by list-regions. Use the same region for sizes, S3 verification and creation. Omit for the default backend.",
      +  "format": "uuid",
      +  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +  "type": "string"
      +}
    • addedInput schema / properties / s3Storage / additionalProperties
      Added value: +false
    • addedInput schema / properties / s3Storage / properties / backups / additionalProperties
      Added value: +false
    • changedInput schema / properties / s3Storage / properties / backups / description
      Previous value: -"Customer-owned bucket and optional key prefix for backups."New value: +"Destination for backups."
    • addedInput schema / properties / s3Storage / properties / backups / properties / bucket / description
      Added value: +"Customer-owned S3 bucket."
    • addedInput schema / properties / s3Storage / properties / backups / properties / path / description
      Added value: +"Optional object-key prefix; defaults to the bucket root."
    • addedInput schema / properties / s3Storage / properties / data / additionalProperties
      Added value: +false
    • changedInput schema / properties / s3Storage / properties / data / description
      Previous value: -"Customer-owned bucket and optional key prefix for data."New value: +"Destination for table data."
    • addedInput schema / properties / s3Storage / properties / data / properties / bucket / description
      Added value: +"Customer-owned S3 bucket."
    • addedInput schema / properties / s3Storage / properties / data / properties / path / description
      Added value: +"Optional object-key prefix; defaults to the bucket root."
    • removedInput schema / properties / s3Storage / properties / externalId
      Removed value: -{
      -  "description": "External ID required by the IAM role trust policy. It must exactly match the value configured in AWS.",
      -  "maxLength": 1224,
      -  "minLength": 2,
      -  "pattern": "^[A-Za-z0-9_+=,.@:/-]+$",
      -  "type": "string"
      -}
    • changedInput schema / properties / s3Storage / properties / roleArn / description
      Previous value: -"ARN of the customer IAM role that RawTree may assume to access the configured buckets."New value: +"ARN of the customer IAM role RawTree may assume."
    • changedInput schema / properties / s3Storage / required
      Previous value: -[
      -  "data",
      -  "backups",
      -  "roleArn",
      -  "externalId"
      -]New value: +[
      +  "data",
      +  "backups",
      +  "roleArn"
      +]
    • addedInput schema / properties / s3StorageAccess
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Creation-only S3 storage identity overrides. Omit to let the API generate values. Custom storage requires externalId matching verification.",
      +  "properties": {
      +    "externalId": {
      +      "description": "Immutable S3 storage External ID. The API generates it when omitted for managed storage; required for custom storage.",
      +      "maxLength": 1224,
      +      "minLength": 2,
      +      "pattern": "^[A-Za-z0-9_+=,.@:/-]+$",
      +      "type": "string"
      +    },
      +    "resourceTag": {
      +      "description": "Immutable rawtree.com/cluster tag value for S3 storage access. Generated by the API when omitted.",
      +      "maxLength": 256,
      +      "minLength": 1,
      +      "pattern": "^[a-z0-9][a-z0-9-]*$",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  3. Addedv0.3.2

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover readOnly=false, idempotentHint=false and destructive=false; the description goes well beyond by disclosing asynchronous provisioning, vertical-only autoscaling with fixed replica count, the customer IAM role / resourceTag tagging requirement, org-admin token auth, and the non-idempotent retry hazard. It also explains which values the API generates versus which the MCP client forwards, which is behavior no annotation or schema field conveys.

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

Conciseness4/5

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

Bold section labels (Purpose, Returns, Behavior, Auth, Safety, Reliability) make a long definition scannable and front-load the outcome before the constraints. It is dense rather than padded, though a few points repeat across Behavior and Safety (externalId generation and reuse), which could be trimmed.

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

Completeness5/5

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

For a nine-parameter nested mutation with no output schema, the definition covers ordering constraints, defaults, identity generation, auth scope, and failure recovery. An agent has everything needed to call it correctly and to avoid the non-idempotent retry trap.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: s3Storage is optional and omitting it means RawTree-managed storage, idleTimeoutMinutes falls back to a server default, and s3StorageAccess.externalId is generated for managed storage yet mandatory for custom storage matching the trust policy. It also ties minimumSize/maximumSize to the list-cluster-sizes catalog and explains that tag values must be applied to customer buckets and roles, which the schema does not state.

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

Purpose5/5

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

The opening line states a specific verb and resource ('Provision a new RawTree dedicated cluster in an organization') and the Returns section clarifies the synchronous/asynchronous split, routing the agent to get-cluster for progress. That distinguishes it from siblings like get-cluster, list-clusters and update-cluster without needing the schema.

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

Usage Guidelines5/5

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

Usage is spelled out as an ordered prerequisite chain: list-cluster-regions first, then list-cluster-sizes, then verify-cluster-s3-access with identical configuration, all reusing the same regionId. It also states the human-confirmation requirement and the exception (explain the server default when idleTimeoutMinutes is omitted), plus a reconciliation path via list-clusters when the response is ambiguous.

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