agnes-video-25-mcp

PyPI

MCP server wrapping Agnes Video 2.5 / 2.5 Flash with reference-mode support (mode=text|keyframe|reference, images/audio/video references)

Versions collected1

Direct dependencies3From release 0.2.5

Last observed21 Oct, 09:16 UTC

README

Version 0.2.5 documentation

Agnes Video 2.5 MCP Service

Standalone MCP server wrapping Agnes Video 2.5, Agnes Video 2.5 Flash, and Agnes Video v2.0 (whitelist, since v0.2.0). First-class reference mode support (image / audio / video reference via images[] / audios[] / videos[] arrays and <Picture N> / / prompt placeholders) is available on 2.5 / 2.5 Flash; v2.0 uses its own protocol (ti2vid/keyframes+extra_body.image[]`) which the server translates transparently — callers keep the unified input shape.

This service is independent of hosted_mcps/agnes-mcp-studio/ (which targets the legacy agnes-video-v2.0 model via the older ti2vid / keyframes API). Run it alongside or replace — both can coexist.

When to use this service

Need	Use this service	Use `agnes-mcp-studio`
Reference-mode video (images / audios as visual + audio anchors)	✅ (2.5 / 2.5 Flash)	❌ (only `extra_body.image` keyframes)
First / last frame control (`first_frame` / `last_frame`)	✅ (2.5 / 2.5 Flash / v2.0)	✅ (raw `ti2vid` / `keyframes`)
Legacy v2.0 model (back-compat with existing pipelines)	✅ (0.2.0+ whitelist; unified inputs)	✅ (raw v2.0 protocol)
Image generation (text-to-image, image edit, 2.5-flash)	✅	✅ (parallel surface)

Install

cd hosted_mcps/agnes-video-25
uv sync                # installs the package + dependencies

Run standalone (stdio MCP)

uv run agnes-video-25-mcp

Wire into `.mcp.json`

Add alongside multimedia-creator:

{
  "mcpServers": {
    "multimedia-creator": { /* existing agnes-mcp-studio entry */ },
    "agnes-video-25": {
      "command": "uv",
      "args": [
        "--directory", "/absolute/path/to/hosted_mcps/agnes-video-25",
        "run", "agnes-video-25-mcp"
      ],
      "env": {
        "AGNES_API_KEY": "sk-your-key-here",
        "AGNES_BASE_URL": "https://api.agnes-ai.cn/v1"
      }
    }
  }
}

Environment variables

Variable	Required	Default	Notes
`AGNES_API_KEY`	yes	—	Same key works for `.agnes-ai.cn` (CN) or `.agnes-ai.com` (intl) — pick the matching `AGNES_BASE_URL`.
`AGNES_BASE_URL`	no	`https://api.agnes-ai.cn/v1`	API root. CN / intl keys are not interchangeable.
`AGNES_OUTPUT_DIR`	no	`./outputs`	Where downloaded media land (videos → `<dir>/videos/`, images → `<dir>/images/`). Use an absolute path for predictable layouts.

Tools

Tool	Purpose
`agnes25_video_generate`	Submit video generation task only (`mode="text" \| "keyframe" \| "reference"`). Returns `{video_id, model_id, submit_key_masked}` — pair with `agnes25_video_query` for status / download.
`agnes25_video_query`	Poll video task status by id. Pass `force_key_masked` (from `agnes25_video_generate`'s `submit_key_masked`) so the poll reuses the submitting key. Optional `download=True` saves to `AGNES_OUTPUT_DIR/videos/`.
`agnes25_image_generate`	Generate images (text-to-image + optional img2img via `image_paths`)
`agnes25_image_edit`	Edit images via `image_paths` + optional `mask_path` (inpainting)
`agnes25_upload_image`	Upload a local file to `img.remit.ee` and return the public HTTPS URL

Full schema: see SKILL.md. Public docs:

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases

Version	Published	Direct dependencies	Open version
0.2.5	27 Sept 2026	3

Package advisories

No matching advisories collected

This describes our collected data; it is not a security assessment.

Metadata history

Meaningful changes

Current collected state Current

Observed since 21 Oct, 09:16 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:74c57b4f17288b82adb3f7611fd4516c31320d43f4da24125ad5c7f376ad81d9