Dactic for Gemini CLI
io.dactic/dactic-mcp
Connect AI clients to your Dactic work context through a hosted MCP service.
client:Gemini CLI
transport:streamable-http
tools:34
Install Dactic in Gemini CLI
~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json
{
"mcpServers": {
"dactic-mcp": {
"httpUrl": "https://mcp.app.dactic.io/mcp"
}
}
}Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs
What Gemini CLI can do once it is connected
- 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
- get_skill_usage
- synthesize_agent
- create_agent_from_process
- get_task_status
- search
- fetch
- get_usage
- get_sync_status
- get_feedback_status