Skip to main content
Glama
speakai

Speak AI MCP Server

Official
by speakai
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Create Automation

create_automation

Create an automation rule with a trigger and ordered steps (magic prompt, translation, filter, upload) for processing transcriptions.

Instructions

Create a new automation rule using the V2 graph model (trigger + ordered steps). Fetch valid step/trigger options with list_automation_triggers / list_automation_actions if unsure.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesDisplay name for the automation
stepsYesOrdered array of graph steps (1-20). Each step is an object: { stepId: string (unique within the array), stepType: one of "magic-prompt" | "translation" | "filter" | "composio-action" | "speak-upload", dependsOn?: string[] (stepIds this step runs after) } plus ONE payload key matching stepType: - magic-prompt -> magicPrompt: { prompt (required unless fieldIds given), title?, assistantType? ("general"|"researcher"|"marketer"|"sales"|"recruiter"|"custom", default "general"), assistantTemplateId? (required if assistantType="custom"), fieldIds?: string[] (max 10, for field extraction) } - translation -> translation: { targetLanguage: BCP-47 code, e.g. "es" } - filter -> filter: { logic: "AND"|"OR", rules: [{ field, op: "eq"|"neq"|"contains"|"ncontains"|"startsWith"|"gt"|"lt"|"exists", value? }] } - composio-action -> composio: { app, action, connectedAccountId?, argsTemplate? } (Composio is currently behind a server flag and may be unavailable) - speak-upload -> speakUpload: { folderId, sourceMode: "url"|"file", sourceUrl? (required when sourceMode="url"), name?, fieldsMap?, language? }
runTypeNoRun type: "instant" (default, runs on trigger) or "schedule" (cron)
triggerYesTrigger object. For folder-based automations: { type: "folders", folderIds: string[] } (at least one folder is required). Note: only "folders" is currently supported for multi-step automations via the API — "tags"/"keywords" are rejected, and "composio"/"webhook" triggers (provider, app, triggerSlug, webhookId, childKey, connectedAccountId) are gated by server flags.
isActiveNoWhether the automation is active (defaults to true)
scheduleNoRequired when runType="schedule": { timePeriod: "today"|"yesterday"|"last7days"|"last14days"|"thisWeek", repeatAt: string }
descriptionNoOptional description

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoResponse payload from the Speak AI API

Tool Definition Quality

A3.9/5.0
Behavior3/5

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

Annotations already indicate mutation (readOnlyHint=false) and no destructiveness. Description adds that it uses the V2 graph model, but does not disclose failure modes, validation rules, or side effects beyond creation.

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

Conciseness5/5

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

Two sentences with no redundancy: first states purpose, second gives usage tip. Every word earns its place.

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

Completeness3/5

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

Given the tool's complexity (nested steps, trigger, 7 parameters) and existence of output schema, the description is minimal. It covers high-level purpose and a usage hint, but could elaborate on the graph model structure. Schema and output schema compensate.

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 the input schema already fully documents all 7 parameters including types, enums, and constraints. The description does not add extra meaning beyond the schema.

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?

Clearly states 'Create a new automation rule using the V2 graph model', specifying the verb and resource. Distinguishes from sibling create tools (e.g., create_folder, create_recorder) by focusing on automations.

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?

Provides explicit guidance: 'Fetch valid step/trigger options with list_automation_triggers / list_automation_actions if unsure.' This helps the agent know prerequisite steps, though does not explicitly exclude other tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/speakai/speakai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server