Using the MCP Server¶
Use this guide when your primary goal is agent integration confidence, not CLI-first workflows.
Why This Matters¶
MCP gives your agent direct access to Sage discovery and workflow tools through a stable protocol boundary.
Where This Fits in the Loop¶
This guide is part of Discover and Use.
Step 1: Start Sage MCP¶
For MCP runtimes, configure Sage as:
- command:
sage - args:
["mcp", "start"]
Step 2: Verify Tool Availability¶
You should see tool families like discovery, skills, prompts, governance, and hub operations.
Step 3: Smoke Test a Tool Call¶
If this returns JSON successfully, your MCP bridge is working end-to-end.
Step 4: Use Read-Only First¶
Start with read-only discovery tools before enabling write paths:
search_skillssearch_promptslist_librariesget_prompt
This reduces integration risk while you validate relevance and output quality.
Step 5: Add Write Paths Deliberately¶
After read-only confidence:
- Enable draft/propose workflows.
- Keep execution behind human or governance approval.
- Add clear policy for when agents can publish, propose, or execute.
Integration Modes¶
- Assisted: MCP read/search only; humans decide all writes.
- Collaborative: agents draft/suggest; humans execute.
- Autonomous: agents act within explicit governance/runbook guardrails.
For full runtime-specific guidance: - Integrating Your Agent
Troubleshooting¶
If tools do not appear or calls fail: