io.github.yagyaanshK/reclip
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RECLIP_MCP_DOWNLOAD_DIR | No | The absolute path to the directory where downloads will be saved. Defaults to ~/Downloads/ReClip if not set. | ~/Downloads/ReClip |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_mediaA | Inspect a public media URL and return normalized metadata and available formats without downloading it. |
| download_mediaA | Download a complete authorized media item locally as MP4 video or MP3 audio. This writes a file and can use significant bandwidth and storage. |
| download_clipA | Download only a precise authorized time range locally as MP4 video or MP3 audio. Timestamps support SS, MM:SS, or HH:MM:SS.000. |
| list_supported_sitesA | List or search extractor names provided by the locally installed yt-dlp version. An extractor name indicates potential support, not a permanent compatibility guarantee. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: inspecting metadata, downloading full media, downloading a time-range clip, and listing supported sites. No overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern with lowercase and underscores (inspect_media, download_media, download_clip, list_supported_sites). The naming is predictable and uniform.
With only 4 tools, the server is tightly scoped to its core functionality: inspection, full download, clip download, and site support discovery. This is an appropriate count for a focused media downloader, well within the ideal 3-15 range.
The tool surface covers the essential workflows: inspecting media, downloading full items, downloading clips, and checking site support. Minor gaps like subtitle downloading exist, but the core lifecycle is complete and agents can accomplish the primary tasks without dead ends.