Skip to main content
Glama

Modellix Media Generation

Server Details

Generate and edit images, videos, and audio with the Modellix API.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2026-07-28
URL
Repository
Modellix/modellix-plugin
GitHub Stars
1
ChatGPT
–
Claude
–

TDQS

A4/5.0

Scored across 8 tools

Disambiguation5/5

Each tool targets a distinct resource+action: file operations (upload/list/delete), model discovery (list_models/get_schema), and task lifecycle (submit/get/wait). The only near-pair, get_task vs wait_task, is clearly separated by non-blocking snapshot versus blocking wait, and descriptions reinforce this.

Naming Consistency5/5

All eight tools use the same modellix_ prefix followed by a consistent verb_noun snake_case pattern (list_files, get_schema, submit_task, wait_task). No camelCase or stylistic deviations.

Tool Count5/5

Eight tools is well within the ideal range and each maps to a necessary step in the media generation workflow: discover model, read schema, upload asset, submit, poll/wait, manage files. No redundant or filler tools.

Completeness4/5

The surface covers the full core lifecycle: file upload/list/delete, model listing plus schema retrieval, and task submit/get/wait. Minor gaps exist, such as no task cancellation or bulk task listing, but agents can work around these.

Available Tools

8 tools
modellix_delete_fileA
DestructiveIdempotent
Inspect

Permanently delete exactly the explicitly selected file_id after user approval. Never delete other files to free quota automatically. An absent file is a successful already_absent result.

Inputs: file_id (required). Returns: object

modellix_get_schemaA
Read-onlyIdempotent
Inspect

Read the public executable input schema for an exact provider/model slug. No API key is forwarded to the schema host. Preserve required fields, defaults and references when preparing input.

Inputs: model_slug (required). Returns: object

modellix_get_taskA
Read-onlyIdempotent
Inspect

Read one task snapshot immediately, without waiting or submitting. Resources may expire; save required outputs promptly.

Inputs: task_id (required). Returns: object

modellix_list_filesC
Read-onlyIdempotent
Inspect

List the current team's uploaded files with pagination. Reuse existing file URLs where appropriate; defaults may retain files for 7 days.

Inputs: limit, offset. Returns: object

modellix_list_modelsA
Read-onlyIdempotent
Inspect

Discover available media models with filters and pagination. Choose a precise slug before reading its schema. Prices, when present, are indicative.

Inputs: type, limit, offset, keyword. Returns: object

modellix_submit_taskAInspect

Submit one paid media generation request after user confirmation of the model and input. Returns task_id immediately. Never retry an unknown submission automatically; query or wait using the known ID.

Inputs: input (required), model_slug (required). Returns: object

modellix_upload_fileAInspect

Upload a public URL or base64_content with filename, at most 16 MiB (16777216 bytes). No local filesystem paths. Reuse returned URLs in model input. Default team limits: 10 files, 2 concurrent uploads, 7-day retention; configuration may vary. On 429, list files and explicitly delete only unneeded IDs; no automatic cleanup.

Inputs: url, filename, base64_content. Returns: object

modellix_wait_taskA
Read-onlyIdempotent
Inspect

Wait up to timeout seconds (default 30, maximum 45) for an existing task. A normal timeout returns the current snapshot and task_id; continue waiting on that ID instead of resubmitting.

Inputs: task_id (required), timeout. Returns: object

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.