terminal-love-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token to raise rate limit for get_repo_stats | |
| TTROVE_CACHE_DIR | No | Directory where HTML/catalog cache lives (default: OS tmp) | |
| TTROVE_LOG_LEVEL | No | Pino log level (default info) | |
| TTROVE_CACHE_TTL_MS | No | Cache lifetime in milliseconds (default 6h) |
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 |
|---|---|
| get_toolA | Full Terminal Trove details for a tool: description, GitHub, language, license, platforms, tags, install commands, and screenshot URLs. |
| search_toolsB | Search the Terminal Trove catalog. Returns tool summaries (slug, name, tagline, thumbnail URL). Uses the site's Typesense search API. |
| related_toolsA | Find tools related to a given slug. Falls back to fetching the tool's primary category page and returning other tools in that category (excluding the input slug). |
| get_repo_statsA | Fetch GitHub repository statistics for a Terminal Trove tool: stars, forks, open issues, language, license, last push, and topics. Provide github_url, slug, or both. |
| list_categoriesA | List all tool categories available on Terminal Trove. Returns slug, name, and URL for each category. |
| browse_categoryA | Browse tools in a Terminal Trove category. Returns slug, name, URL, and description for each tool. Use list_categories first to discover valid category slugs. |
| newly_addedA | Returns the most recently added terminal tools from terminaltrove.com/new/, newest first. Each entry includes slug, name, URL, and description. |
| tool_of_the_weekA | Returns the current Terminal Tool of the Week plus an archive of past picks from terminaltrove.com/tool-of-the-week/. Each archive entry includes the date label (e.g. 'June 2, 2026'). |
| list_screenshotsA | List all screenshot / demo-GIF metadata (url, type, alt, dimensions) for a Terminal Trove tool. Use this before view_screenshot to pick an index. |
| view_screenshotA | Fetch a TUI screenshot or demo GIF from Terminal Trove and return it as an inline image so you can visually inspect the design. Provide slug (+ optional index) OR a cdn.terminaltrove.com url directly. |
| sync_catalogA | Fetches the full Terminal Trove catalog from sitemap + /list/ and builds a local index for fast offline search. Returns the tool count, build timestamp, and a 10-item sample. Pass force=true to force a rebuild even if the index is fresh. |
| search_catalogA | Fuzzy-searches the local Terminal Trove catalog index by tool name or slug. The search is fully offline after the first sync_catalog call — no network required. Returns matching tools with their score (0 = perfect). |
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 12 tools
Each tool has a clearly distinct purpose: browsing, searching, viewing details, screenshots, stats, etc. The two search tools are differentiated by offline/online mode. No ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., browse_category, get_repo_stats, list_categories). No mixing of conventions.
12 tools is well-scoped for a catalog browsing service, covering all necessary operations without being overwhelming or too sparse.
The tool set fully covers browsing, searching, and inspecting Terminal Trove tools with no missing operations. It is a read-only service, so it's complete for its domain.