ScreenApp Legacy MCP Bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCREENAPP_MCP_URL | No | Override the legacy MCP URL for testing. | |
| SCREENAPP_ACCESS_TOKEN | No | Use a short-lived token directly; takes precedence over saved credentials. | |
| SCREENAPP_API_BASE_URL | No | Override the legacy REST base URL for testing. | |
| SCREENAPP_OAUTH_ISSUER | No | Override OAuth discovery for testing. | |
| SCREENAPP_OAUTH_RESOURCE | No | Override the OAuth resource when testing a different MCP URL. | |
| SCREENAPP_CREDENTIALS_FILE | No | Override the file-store path. | |
| SCREENAPP_CREDENTIAL_STORE | No | Credential store to use: 'keychain' or 'file'. | |
| SCREENAPP_KEYCHAIN_ACCOUNT | No | Override the Keychain account label. | |
| SCREENAPP_KEYCHAIN_SERVICE | No | Override the Keychain service name. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_recordingsA | List recordings from the last active ScreenApp team or a specified team. |
| get_recordingA | Get metadata for one legacy ScreenApp recording. Use get_transcript for transcript text and get_summary for its stored summary. |
| get_transcriptB | Read an existing transcript. Long transcripts are paginated; continue with nextOffset while hasMore is true. |
| search_recordingsA | Search existing transcript text without asking ScreenApp to generate an AI answer. |
| get_profileA | Read the profile for the authenticated ScreenApp account. Useful for confirming which account OAuth selected. |
| list_teamsA | List teams available to the authenticated ScreenApp account. |
| get_teamA | Read details for one ScreenApp team. |
| get_usage_statsA | Read ScreenApp usage and billing counters. This does not consume credits. |
| get_summaryA | Read the summary ScreenApp already stored for a UUID recording. This is read-only and does not generate an answer or consume Ask AI credits. |
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 9 tools
Most tools target distinct resources and actions, and get_recording explicitly points to get_transcript and get_summary. The only possible confusion is between list_recordings and search_recordings, but the descriptions clarify that search is transcript-text based.
All tool names follow a consistent verb_noun snake_case pattern: list/get/search. This makes the tool API predictable and easy for an agent to navigate.
Nine tools is well-scoped for a read-only legacy bridge covering recordings, transcripts, summaries, teams, profile, and usage. Each tool serves a clear purpose without unnecessary bloat.
For the apparent read-only bridge purpose, the surface is complete: discovery, metadata, transcript, summary, team, account, and usage data are all covered. There are no obvious dead ends for a legacy data-access workflow.