Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
POE_API_KEYYesYour Poe API key. Required to run the server.
POE_BASE_URLNoPoe API endpoint, useful for testing.https://api.poe.com/v1
POE_OUTPUT_DIRNoWhere generated media files are saved.~/poe-media
POE_TIMEOUT_MSNoRequest timeout in milliseconds. Video generation can be slow.600000
POE_IMAGE_MODELNoDefault image bot used by generate_image.GPT-Image-1
POE_MUSIC_MODELNoDefault music bot used by generate_music.Lyria
POE_VIDEO_MODELNoDefault video bot used by generate_video.Veo-3
POE_SPEECH_MODELNoDefault speech bot used by generate_speech.ElevenLabs
POE_INLINE_IMAGE_MAX_BYTESNoLargest image size in bytes that is returned inline to Claude.768000

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_imageA

Generate an image from a text prompt with a Poe image bot (default: GPT-Image-1; others include FLUX-pro-1.1-ultra, Imagen-4-Ultra, Ideogram-v3, Seedream-4.0, Nano-Banana). Pass reference_images to edit or remix existing pictures. Files are saved locally and their paths returned.

generate_videoA

Generate a video clip from a text prompt with a Poe video bot (default: Veo-3; others include Sora-2, Kling-2.1-Master, Runway-Gen-4-Turbo, Hailuo-02, Veo-3-Fast). Optionally animate a start image. Video can take several minutes.

generate_speechA

Turn text into spoken audio with a Poe text-to-speech bot (default: ElevenLabs; others include ElevenLabs-v3, Hailuo-Speech-02, OpenAI TTS bots). Saves an audio file locally.

generate_musicB

Compose music or sound from a text prompt with a Poe music bot (default: Lyria; others include ElevenLabs-Music, Stable-Audio-2.5, MiniMax music bots). Describe genre, mood, tempo and instruments.

generate_with_poe_botA

Call any Poe bot by name with a prompt and optional local file attachments, then download whatever media it returns. Use for bots the dedicated tools don't cover (upscalers, lip-sync, sound effects, background removal...).

list_poe_modelsA

List bot/model names available through the Poe API, optionally filtered by a search term (e.g. 'veo', 'image', 'eleven').

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A3.8/5.0

Scored across 6 tools

Disambiguation4/5

The four generate_<media> tools each target a clearly distinct media type (image, video, speech, music), and list_poe_models is obviously a discovery tool. The only overlap is generate_with_poe_bot, which functionally could do anything the dedicated tools do, but its description explicitly scopes it to uncovered bots (upscalers, lip-sync, etc.), keeping boundaries workable.

Naming Consistency4/5

Snake_case is used throughout, and five of six tools share the generate_ prefix with a clear verb_noun structure (generate_image, generate_video, etc.). list_poe_models follows the noun-query convention and generate_with_poe_bot is slightly longer but still predictable.

Tool Count5/5

Six tools is well-scoped for a media generation server: one per media type, a model discovery tool, and a generic fallback. No redundant or filler tools, and each earns its place.

Completeness4/5

The surface covers image, video, speech, and music generation plus model discovery and a catch-all bot invoker for edge cases, which is strong coverage. The main gap is any explicit job status/retrieval for slow video generation, but the generic tool provides a workaround.

Maintenance

ActivityMaintained
ResponsivenessNo issues