review-bench/davidortinau_sentencestudio/mcp-tool-discovery
Claude Code and agent skill by review-bench/davidortinau_sentencestudio
- community
Checking that the SKILL.md file is still in the repository.
MCP server tool discovery and usage patterns for this environment
Install
npx vskill@latest install review-bench/davidortinau_sentencestudio/mcp-tool-discoverySKILL.md
The same SKILL.md was published earlier as davidortinau/sentencestudio/mcp-tool-discovery.
Context
This project has multiple MCP (Model Context Protocol) servers configured, providing tools beyond basic file/shell operations.
Available MCP Servers
GitHub MCP Server (github-mcp-server-*)
Status: ✅ Available Key tools:
search_code— Search code across GitHub repossearch_issues/search_pull_requests— Find issues and PRslist_issues/issue_read— Read issue detailslist_pull_requests/pull_request_read— PR details, diffs, reviewsget_file_contents— Read files from GitHub reposlist_commits/get_commit— Commit history and diffsactions_list/actions_get/get_job_logs— CI/CD workflow statuslist_copilot_spaces/get_copilot_space— Copilot Spaces
Use when: Issue triage, PR review, code search across repos, CI status checks
Aspire MCP Server (aspire-*)
Status: ✅ Available Key tools:
list_resources— List running Aspire resources (projects, containers)list_console_logs— View resource stdout/stderrlist_structured_logs— Query structured log entrieslist_traces/list_trace_structured_logs— Distributed tracingexecute_resource_command— Start/stop/restart resourceslist_integrations— Available Aspire NuGet integrationsdoctor— Environment health checkssearch_docs/get_doc/list_docs— Aspire documentation
Use when: Running the app, debugging services, checking health, reading Aspire docs
Playwright MCP Server (playwright-*)
Status: ✅ Available Key tools:
browser_navigate/browser_snapshot/browser_take_screenshot— Page interactionbrowser_click/browser_type/browser_fill_form— UI interactionbrowser_evaluate/browser_run_code— JavaScript executionbrowser_console_messages/browser_network_requests— Debugging
Use when: E2E testing, UI verification, webapp interaction
Microsoft Learn Docs (learndocs-*)
Status: ✅ Available Key tools:
microsoft_docs_search— Search MS Learn documentationmicrosoft_code_sample_search— Find code samplesmicrosoft_docs_fetch— Fetch full documentation pages
Use when: Researching .NET APIs, MAUI features, Azure services, EF Core patterns
Context7 (context7-*)
Status: ✅ Available Key tools:
resolve-library-id— Find library IDs for documentation lookupquery-docs— Query library documentation with code examples
Available libraries: .NET MAUI, MauiReactor, Community Toolkit, SkiaSharp, ElevenLabs Use when: Looking up API usage, code examples, library-specific patterns
Work IQ (workiq-*)
Status: ✅ Available (requires EULA acceptance) Key tools:
ask_work_iq— Query M365 Copilot for emails, meetings, files
Use when: Checking work context, meeting notes, shared files
Hot Reload Sentinel (hotreload-sentinel-*)
Status: ✅ Available Key tools:
hr_watch_start/hr_watch_stop/hr_watch_follow— Monitor hot reloadhr_diagnose/hr_status/hr_report— Diagnose hot reload issueshr_pending_atoms/hr_record_verdict— Track change confirmations
Use when: Debugging hot reload issues, monitoring live development sessions
Routing Rules
- Coordinator handles directly: Simple MCP reads (status checks, single queries)
- Spawn with MCP context: When task needs agent expertise AND MCP tools
- Explore agents never get MCP: Route MCP work to general-purpose agents
- Graceful degradation: If MCP tool missing, fall back to CLI (
gh,az, etc.)
Anti-Patterns
- Don't use MCP when CLI is simpler —
gh issue listis often faster than MCP for simple queries - Don't assume MCP availability — always degrade gracefully
- Don't pass MCP context to explore agents — they can't use it
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.squad/skills/mcp-tool-discovery/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/review-bench/davidortinau_sentencestudio/mcp-tool-discovery)