Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_EXENoFull path to the ollama executable
OLLAMA_HOSTNoOllama addresshttp://localhost:11434
VISION_FONTNoFont used by the health-check image
VISION_YTDLPNoFull path to yt-dlp
OLLAMA_MODELSNoModel dir (disk check)~/.ollama/models
VISION_CONFIGNoPath to the configuration file
VISION_FFMPEGNoFull path to ffmpeg
VISION_API_KEYNoAPI key for the endpoint
VISION_API_BASENoOpenAI-compatible endpoint, e.g. http://localhost:11434/v1
VISION_MCP_CACHENoPersist MCP results to disk (hits across server restarts)true
VISION_KEEP_ALIVENoModel residency (0 = unload immediately)10m
VISION_MAX_TOKENSNoOutput budget for transcription mode98304
VISION_SPEECH_ENVNoConda env name for speechfunasr
VISION_TEXT_MODELNoOCR / transcription modelhaervwe/GLM-4.6V-Flash-9B
VISION_QUICK_MODELNoFast image/video modelqwen3.5:4b
VISION_QUICK_THINKNoEnable Qwen thinking modefalse
VISION_MAX_IMAGE_MBNoLocal/stdin image size cap (MB)20
VISION_BUDGET_PIXELSNoPixel budget; frames drop automatically20000000
VISION_MCP_CACHE_DIRNoMCP disk-cache directory
VISION_SPEECH_PYTHONNoFull path to the speech interpreter
VISION_MAX_DURATION_HNoVideo/audio duration cap (hours); longer inputs rejected; 0 disables6
VISION_MAX_DOWNLOAD_MBNoRAM cap for unknown-type URL buffering500
VISION_SINGLE_RESIDENTNoKeep only one model resident (VRAM)true
VISION_QUICK_MAX_TOKENSNoOutput budget for quick mode16384

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": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
describe_imageA

Describe or understand one or more images with a local vision model (scene, objects, colors, UI, etc.). Returns JSON: {"text": ..., "mode": "image", "media": [...]}.

transcribeA

Verbatim transcription of text in images/documents/screenshots/video subtitles (no summary, judgment, or interpretation). Returns JSON with text and, for videos, frame timestamps.

analyze_videoA

Analyze a video with a local vision model: scenes, actions, time-window deep reading, contact sheets, etc. Returns JSON: {"text": ..., "mode": ..., "frames": [{"t": ..., "w": ..., "h": ...}], "duration": ...}.

transcribe_audioA

Speech-to-text (FunASR SenseVoice, with timestamps; embedded subtitle tracks are preferred when available). Returns JSON: {"text": ..., "source": "asr"|"subtitle"}.

vision_statusA

Show the vision backend status (models, backend type, ffmpeg, speech environment, GPU, watchdog).

vision_checkA

Run the environment health check (image reading, transcription, video sampling; can be slow).

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

Each tool targets a distinct medium or task: image understanding, text extraction, video analysis, audio transcription, and system diagnostics. Minor overlap exists between describe_image and analyze_video for video content, but descriptions clearly separate by media type.

Naming Consistency2/5

Tool names mix conventions: three use verb_noun (describe_image, analyze_video, transcribe_audio), one is a bare verb (transcribe), and two use a vision_ prefix (vision_status, vision_check). This inconsistency makes the set feel less predictable.

Tool Count5/5

Six tools is well-scoped for a multimodal sensing server. Each tool has a clear purpose and none feel redundant or unnecessary.

Completeness4/5

The set covers the core sensing lifecycle: image description, video analysis, audio/speech transcription, and health checks. Minor gaps like general audio analysis or dedicated frame extraction are absent but not essential for the stated purpose.

Maintenance

ActivitySlowing
ResponsivenessNo issues