Choose Your Path
Pick the row that matches your goal. Each path has its own reading order and first commands.
Quick-reference decision table
| Goal | Time investment | Start with |
|---|---|---|
| See it work in 5 minutes | Minimal | Path 1 — First run |
| Host the runtime on your own machine | Low–medium | Path 2 — Loopback-hosted runtime |
| Remote runtime with auth | Medium | Path 3 — Remote runtime auth |
| MCP integrations | Medium | Path 4 — MCP |
| Enterprise evaluation | High | Path 5 — Enterprise |
1. First successful run
Choose this if: You want the smallest possible setup and a working command tree in minutes.
What you get: A generated CLI from a sample OpenAPI file, running through a locally hosted open-cli-toolbox runtime.
Reading order:
- Installation — install the two binaries
- Quickstart — create a config, start the runtime, run
catalog list, inspect the generated command tree
First commands to run:
open-cli-toolbox --config ./.cli.json --addr 127.0.0.1:8765
open-cli --runtime http://127.0.0.1:8765 --config ./.cli.json catalog list --format pretty
Read this next: CLI overview to understand the full command model.
2. Loopback-hosted runtime
Choose this if: You are evaluating the supported hosted-runtime model on a laptop or single machine before moving it to shared infrastructure.
What you get: open-cli-toolbox hosted on loopback; open-cli still points at it by URL, so the contract matches every other deployment.
Reading order:
- Complete Path 1 first
- Runtime overview
- Deployment models
- Operations overview
Read this next: Tracing and instances to understand state directories, audit paths, and runtime metadata.
3. Remote runtime auth and scoped access
Choose this if: The runtime is hosted separately and access must be authenticated (bearer tokens, scoped catalogs, browser login).
What you get: Runtime bearer auth, catalog filtering, and Authentik-based login working together around open-cli-toolbox.
Reading order:
- Complete Path 2 first
- Security overview
- Authentik reference proof
Read this next: Fleet validation to see which auth paths are CI-reproducible.
4. MCP integrations
Choose this if: You care about MCP stdio or streamable HTTP servers connecting through open-cli-toolbox.
What you get: Understanding of which MCP paths are available, which are proven in CI, and how to configure them.
Reading order:
- Complete Path 2 first
- Discovery & Catalog overview
- Deployment models
- Fleet validation — especially important here, as it shows which MCP paths are CI-reproducible vs. needing live proof
Read this next: Operations overview for runtime observability alongside MCP.
5. Enterprise readiness evaluation
Choose this if: You need a review path you can hand to operators, security reviewers, or buyers — covering hosted deployment, proof of functionality, and audit trails.
What you get: A structured path through real auth, runtime, validation, and policy evidence.
Reading order:
- Enterprise readiness — capabilities overview for evaluators
- Authentik reference proof — real auth flow evidence
- Fleet validation — CI-reproducible end-to-end proof
- Security overview — policy, secrets, and audit logging
Read this next: Deployment models for the supported hosted-runtime topologies.