Skip to main content
Glama
speakai

Speak AI MCP Server

Official
by speakai

Ask AI About Your Recordings

ask_magic_prompt

Query your media files with natural language questions using AI. Supports single files, folders, or entire workspace with specialized assistant roles for tailored answers.

Instructions

Ask an AI-powered question about your media using Speak AI's Magic Prompt. Supports querying a single file, multiple files, entire folders, or your whole workspace. Pass mediaIds for specific files, folderIds for entire folders, or omit both to search across all media. Use assistantType to get specialized responses (e.g., 'researcher' for academic analysis, 'sales' for deal insights). To continue a conversation, pass the promptId from a previous response. Returns a promptId — save it to continue the conversation with follow-up questions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoFilter media by tags
promptYesThe question or prompt to ask about the media
endDateNoEnd date for date range filter (ISO 8601, e.g., '2025-03-31')
fieldIdNoScope the prompt to a single custom field
filtersNoAdvanced filter object to scope which media the prompt runs over
fieldIdsNoScope the prompt to multiple custom fields (max 10)
folderIdNoSingle folder ID to scope the query to. Use folderIds for multiple folders.
mediaIdsNoArray of media IDs to query. Omit along with folderIds to search across all media in your workspace.
promptIdNoID of an existing conversation to continue. Pass this to maintain chat context across multiple questions.
speakersNoFilter to specific speaker IDs from the transcript
folderIdsNoArray of folder IDs to scope the query to. Omit along with mediaIds to search across all media.
startDateNoStart date for date range filter (ISO 8601, e.g., '2025-01-01')
assistantTypeNoAssistant persona: 'general' (default), 'researcher' (academic), 'marketer' (content), 'sales' (deals), 'recruiter' (hiring). Use 'custom' with assistantTemplateId.
isIndividualPromptNoWhen true, processes each media file separately instead of combining context. Useful for comparing responses across files.
assistantTemplateIdNoRequired when assistantType is 'custom'. ID of a custom assistant template from list_prompts.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNoResponse payload from the Speak AI API
Behavior4/5

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

The description adds context beyond annotations: it returns a promptId, supports conversations, and scoping options. No contradictions with annotations (readOnlyHint=false, destructiveHint=false). It aligns with the tool's behavior.

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?

The description is a single paragraph but covers all important points: purpose, scoping, assistant types, conversation continuation, and return value. It's efficient and well-structured for an AI agent.

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?

Given 15 parameters with 1 required, nested objects, and an output schema, the description covers core behavior and key parameters. It explains main use cases and return value (promptId), leaving additional parameter details to the schema.

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%, baseline 3. The description adds meaning beyond schema: explains how mediaIds/folderIds/omit work, assistantType options, and promptId for continuation. It provides valuable usage context for key parameters.

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 description clearly states the tool asks an AI-powered question about media using Magic Prompt. It distinguishes from siblings like 'retry_magic_prompt' and 'get_favorite_prompts' by focusing on querying media.

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 when to use (for asking questions about media), how to scope (mediaIds, folderIds, omit for all), how to continue conversations (promptId), and mentions assistantType for specialized responses. It doesn't explicitly say when not to use, but provides clear context.

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