get_skill_usage — Dactic MCP Tool Read-only
get_skill_usage
(get skill usage) is one of 34 tools on the
Dactic
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call get_skill_usage from your client
- Claude Code Dactic get_skill_usage run in your project directory
- Claude Desktop Dactic get_skill_usage ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Dactic get_skill_usage ~/.cursor/mcp.json
- VS Code Dactic get_skill_usage .vscode/mcp.json
- Zed Dactic get_skill_usage ~/.config/zed/settings.json
- Windsurf Dactic get_skill_usage ~/.codeium/windsurf/mcp_config.json
- Cline Dactic get_skill_usage ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Dactic get_skill_usage ~/.gemini/settings.json
- Grok Dactic get_skill_usage .mcp.json (in your project root)
- ChatGPT Dactic get_skill_usage Settings → Connectors → Advanced → Developer mode
- Claude.ai Dactic get_skill_usage Settings → Connectors → Add custom connector
- LangChain Dactic get_skill_usage pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http dactic-mcp https://mcp.app.dactic.io/mcpOther tools on this server
- list_agents
- get_agent
- load_agent
- invoke_agent
- resolve_terms
- check_freshness
- get_policy
- list_skills
- get_skill
- ask_knowledge
- get_context_bundle
- get_user_context
- get_knowledge_provenance
- submit_agent_feedback
- check_against_policy
- synthesize_agent
- create_agent_from_process
- get_task_status
- search
- fetch
- get_usage
- get_sync_status
- get_feedback_status
- recommend_agent
- compare_agent_versions
- find_context_gaps
- get_entity_context
- get_context_delta
- retrieve_similar_cases
- query_work_dataset
- guide_workflow
- recommend_new_agents
- deploy_agent
This list was read from the server itself, by connecting to it and calling tools/list on 11 November 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.