Skip to main content
Glama

Server Details

Make images, video, music and voiceovers with more than 1,000 generation models.

Ownership verified
Status
Healthy
Uptime
33.3% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a distinct role: catalog/pricing (list_models), prompt grammar (prompt_guide), execution (run), polling (get_job), credits (balance), and two clearly separated upload paths split by size/source (upload_file inline vs upload_from_url hosted). The two advisory tools could superficially overlap, but the descriptions make the boundary explicit (model discovery/pricing vs prompt construction/failure modes).

Naming Consistency4/5

Most names follow a verb_noun or verb_target pattern (get_job, list_models, upload_file, upload_from_url) with a bare imperative run, which reads naturally. balance and prompt_guide are noun-form resource names that break the pattern, a minor but noticeable deviation.

Tool Count5/5

Seven tools is well-scoped for a generation API: one entry point per job lifecycle stage plus supporting discovery, pricing, and upload tools. Nothing appears redundant or missing at the count level.

Completeness4/5

The core lifecycle is covered end to end: discover models and pricing, shape prompts, upload inputs, submit a run, poll for results, and check credits. Gaps remain around job management—no list-jobs/history or cancel/abort for queued runs, and no way to re-fetch or manage previously uploaded assets without a stored ref.

Publisher details

Operator
Photoproduct.io · Publisher source
Operator website
https://photoproduct.io
Vendor relationship
First-party
Trust center
Not provided
Restrictions
Sign-in with a Photoproduct.io account (Google). Generations use credits from that account, within a daily limit set per connected app. · Publisher source

Available Tools

7 tools
balanceCredit balanceA
Read-onlyIdempotent
Inspect

Get your credit balance. Runs are charged in whole app credits ($0.10 each), reserved at submission and released if the run fails; buy credits in the app.

Returns: note, credits, agent_token, credits_usd, +2 more

get_jobCheck a generationA
Read-onlyIdempotent
Inspect

Get the status and result of a generation job by its job_ref (returned by run).

Inputs: job_ref (required). Returns: kind, error, model, status, +8 more

list_modelsBrowse modelsA
Read-onlyIdempotent
Inspect

List every available generation model in the catalog with its category, parameters and defaults, which params take uploaded files, and a default-request estimate labelled by price_basis (default_request, input_dependent, or duration_ceiling): cost_credits is what the call bills in whole app credits ($0.10 each), and cost_micros/cost_usd are the same amount in usd_micros and USD. Call this first to discover valid model values and how to price/shape a run call.

Inputs: all, limit, offset, search, +4 more. Returns: note, total, models, offset

prompt_guidePrompt guideA
Read-onlyIdempotent
Inspect

Get the house prompt grammar for a generation job, with the models to use for it and a worked example. Tasks: face_lock, character_outfit, character_sheet, scene_plate, video_scene, video_from_image, video_keyframes, story_bible. Call with no task for the index. Worth calling BEFORE run whenever you are making characters, scenes or video: a malformed request is rejected and a weak prompt wastes a paid generation, and this returns the exact params and the failure modes each grammar exists to prevent.

Inputs: task. Returns: note, tasks

runGenerate mediaAInspect

Run any generation model by name with a params object. Returns a job_ref; poll get_job until completed for the output URL (or result_text for transcription). File-input params (see list_models file_inputs) take an upl_ ref (from POST /api/upload, or the upload_from_url / upload_file tools), the job_ref of an earlier completed job to chain its result into this one, or a hosted URL; transcription/speech-to-text models and models priced by their input's length or size require a ref so the input can be measured. The price depends on the model and params and is charged in whole app credits ($0.10 each): cost_credits in the reply is what is reserved, cost_micros/cost_usd the same amount in usd_micros and USD. The credits are RESERVED when the run is submitted and released again if it fails or is rejected; only a completed run is charged, so a failed generation costs nothing and needs no refund; if your credits do not cover it, buy credits in the app.

Inputs: model (required), params, idempotency_key. Returns: notes, status, job_ref, message, +5 more

upload_fileUpload a fileAInspect

Upload a SMALL file inline as base64 to get a single-use upload_ref for a run file-input param. The bytes are validated (type/size) and duration-probed. Inline is capped at 64MB - use upload_from_url for video or large files.

Inputs: data_base64 (required), filename. Returns: note, media_type, upload_ref, duration_min

upload_from_urlUpload from a linkAInspect

Turn a hosted file URL into a single-use upload_ref: the server fetches, validates (type/size) and duration-probes it, returning an upload_ref to pass as a run file-input param. This is also the way to feed transcription/speech-to-text models from a URL, since they price by measured input length and a bare URL cannot be measured before the job runs.

Inputs: url (required). Returns: note, media_type, upload_ref, duration_min

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources