screen-recorder-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_targetsA | List recordable windows (front-most first) and monitors ( |
| pick_regionA | Show a drag-to-crop overlay over the target so the USER selects the area. |
| start_recordingA | Start recording a window or monitor to MP4 (H.264). |
| recording_statusA | Report the running recording (state, elapsed time, countdown, whether the target closed). |
| pause_recordingA | Pause the running recording; paused time is not recorded. |
| resume_recordingB | Resume a paused recording. |
| stop_recordingA | Stop the running recording and return the final MP4 path ( |
| cancel_recordingA | Stop the running recording and delete the partial file. |
| list_recordingsB | Recording history, newest first, including recordings the user made by hand. |
| trim_recordingB | Cut a recording to [start_seconds, end_seconds]; saves a new file, the original is kept. |
| export_gifC | Convert a recording to an animated GIF and return its path. |
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 11 tools
Each tool targets a distinct lifecycle step or resource: discovery (list_targets, list_recordings), setup (pick_region), capture control (start/pause/resume/stop/cancel), and post-processing (trim_recording, export_gif). The only near-pair is stop_recording vs cancel_recording, and their descriptions make the keep-vs-delete difference explicit. An agent can select the right tool reliably.
Names are uniformly snake_case with clear verb-led phrasing (list_targets, start_recording, pause_recording, trim_recording, export_gif). The lone deviation is recording_status, which is noun-first rather than verb_noun, though it is still readable and unambiguous. Overall predictable.
11 tools is well within the sweet spot and each one maps to a concrete step of the recording workflow. There are no filler or redundant tools; pause/resume/cancel each earn their place as separate operations. The set is nicely scoped to the domain.
The surface covers the full capture lifecycle: target discovery, region selection, start, status, pause/resume, stop, cancel, history, trim, and GIF export. Minor gaps exist — there is no tool to delete a saved recording or inspect its duration/metadata, and no still-frame capture — but agents can work around these. Core workflows are fully supported.