Skip to main content
Glama
RawTree MCP Server

RawTree MCP Server

Official
by rawtreedb

Create Table

create-table
Idempotent

Creates an empty RawTree table in a database, with optional sorting key, TTL retention, and engine settings, so you can start storing and querying structured data.

Instructions

Purpose: Create an empty RawTree table in a database.

Returns: The database and table names, resolved storage destination, sorting_key, ttl (stored expression or null), and settings (explicit {name, value} entries with SQL values and secrets masked by the engine).

Behavior: The table uses the database's storage when the database configures one, and the cluster's default storage otherwise. Storage is configured on the cluster or the database, never per table.

Sorting key: sortingKey is an optional string of comma-separated SQL expressions. Omit it and the table picks a sorting key per part from the ingested data, which suits exploratory tables. Set it when the query pattern is known, listing expressions in key order, lowest cardinality first. Use update-table to change it later.

Configuration: Optional ttl sets row-deletion retention; settings supplies engine settings as string, number, or boolean literals.

Auth: Requires organization admin access. Authorization is enforced by the RawTree API.

Reliability: If the response is ambiguous, call list-tables to reconcile by database and table 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": {
      "name": "<name>"
    },
    "name": "create-table"
  }
}

Input Schema

NameRequiredDescriptionDefault
ttlNoRow-deletion TTL SQL expression, optionally followed by DELETE WHERE <condition>. Subqueries and other TTL actions are unsupported. Omit to leave unchanged on update; null and empty strings cannot remove TTL.
nameYesName of the table to create.
clusterNoRawTree cluster to use for this operation.
databaseNoOptional RawTree database override. RawTree uses the default database when omitted.
settingsNoEngine settings as JSON scalar values. Strings are literal values, not SQL expressions. Updates change supplied settings only; omitted settings are preserved. This route cannot reset settings.
sortingKeyNoOptional comma-separated SQL sorting expressions in key order. Omit it to let the table pick a key per part from the ingested data.
organizationNoRawTree organization containing the target cluster.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.9
    • addedInput schema / properties / settings
      Added value: +{
      +  "additionalProperties": {
      +    "anyOf": [
      +      {
      +        "type": "string"
      +      },
      +      {
      +        "type": "number"
      +      },
      +      {
      +        "type": "boolean"
      +      }
      +    ]
      +  },
      +  "description": "Engine settings as JSON scalar values. Strings are literal values, not SQL expressions. Updates change supplied settings only; omitted settings are preserved. This route cannot reset settings.",
      +  "propertyNames": {
      +    "pattern": "^[A-Za-z_][A-Za-z0-9_]*$",
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / ttl
      Added value: +{
      +  "description": "Row-deletion TTL SQL expression, optionally followed by DELETE WHERE <condition>. Subqueries and other TTL actions are unsupported. Omit to leave unchanged on update; null and empty strings cannot remove TTL.",
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Changed2 schema fields changedv0.4.2
    • removedInput schema / properties / s3Storage
      Removed value: -{
      -  "description": "Optional per-table S3 override. Omit to inherit the database or cluster's default storage.",
      -  "properties": {
      -    "backups": {
      -      "description": "Customer-owned bucket and optional key prefix for backups.",
      -      "properties": {
      -        "bucket": {
      -          "maxLength": 63,
      -          "minLength": 3,
      -          "type": "string"
      -        },
      -        "path": {
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "bucket"
      -      ],
      -      "type": "object"
      -    },
      -    "data": {
      -      "description": "Customer-owned bucket and optional key prefix for data.",
      -      "properties": {
      -        "bucket": {
      -          "maxLength": 63,
      -          "minLength": 3,
      -          "type": "string"
      -        },
      -        "path": {
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "bucket"
      -      ],
      -      "type": "object"
      -    },
      -    "externalId": {
      -      "description": "External ID required by the IAM role trust policy. It must exactly match the value configured in AWS.",
      -      "maxLength": 1224,
      -      "minLength": 2,
      -      "pattern": "^[A-Za-z0-9_+=,.@:/-]+$",
      -      "type": "string"
      -    },
      -    "roleArn": {
      -      "description": "ARN of the customer IAM role that RawTree may assume to access the configured buckets.",
      -      "minLength": 1,
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "data",
      -    "backups",
      -    "roleArn",
      -    "externalId"
      -  ],
      -  "type": "object"
      -}
    • addedInput schema / properties / sortingKey
      Added value: +{
      +  "description": "Optional comma-separated SQL sorting expressions in key order. Omit it to let the table pick a key per part from the ingested data.",
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. Addedv0.3.2

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare non-read-only, idempotent, non-destructive, so the safety profile is covered. The description adds real context beyond them: storage resolution precedence, an organization-admin auth requirement, ttl retention semantics, and retry reconciliation via list-tables when a response is ambiguous. That said, it does not explain why create is marked idempotent (e.g. behavior when the table already exists), which is the single most important unresolved behavioral question for a create tool.

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 make it skimmable and front-loaded, with purpose and return values before the detail. It is on the long side for a create endpoint, and the storage-configuration paragraph is partly background rather than actionable, but no sentence is filler.

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?

No output schema exists, and the description compensates by enumerating the returned fields, including secret masking. Combined with auth, storage precedence, ttl, and failure-recovery guidance, an agent has everything needed to call it and interpret the result.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description reinforces sortingKey ordering intent ('key order, lowest cardinality first') and that ttl sets row-deletion retention, but adds little the schema does not already say about cluster, database, organization, or settings.

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?

States a specific verb and resource ('Create an empty RawTree table in a database') and immediately scopes what the tool does not do (storage is configured on cluster/database, never per table). It also names update-table as the route for changing the sorting key, so an agent can distinguish it from sibling mutation tools.

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?

Gives clear selection guidance for the two optional-but-consequential parameters: omit sortingKey for exploratory tables where keys are picked per part, set it when the query pattern is known; use update-table to change it later. It stops short of stating when to choose create-table over a higher-level alternative such as install-app, so it is not a full when/when-not statement.

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