The
vijil-mcp server is a separate package that uses vijil-console under the hood. Install it separately from vijil-sdk, since the SDK can reuse saved MCP sign-in credentials and gateway settings.Prerequisites
- A Vijil Console deployment, its API gateway URL, and access to a team
- Vijil credentials: a client ID and client secret, or a bearer access token
- A provider API key for the Agent endpoint you want to test
- Claude Code if you choose MCP. See Claude Code setup.
Run Your First Evaluation
1
Install Your Interface
- CLI
- SDK
- REST API
- MCP
Install
vijil-sdk, which includes the vijil CLI:2
Configure and Authenticate
- CLI
- SDK
- REST API
- MCP
Save the Console gateway, then export the API credential pair created in the Console:The CLI exchanges the pair for a bearer token when it creates the client. If you already have a bearer token, set
VIJIL_API_KEY or run vijil auth login and paste the token. Interactive login saves it to ~/.vijil/credentials.json.If your credentials do not resolve a team automatically, pin one in ~/.vijil/config.toml:3
Register an Agent
The example below registers an OpenAI-compatible chat-completions endpoint. Read provider credentials from environment variables in your application code and keep them out of source control.Copy the returned Agent
- CLI
- SDK
- REST API
- MCP
id, then confirm the Agent is available:4
5
Inspect the Results
Continue after the Evaluation succeeds. If it ends as
failed or cancelled, inspect its status and error details before retrieving results.- CLI
- SDK
- REST API
- MCP
Show the completed Evaluation and the Agent’s latest Trust Score:Inspect only the prompt-response rows from failed Probes:
6
Download the Report
You generate Trust Reports on demand after Evaluations complete.
- CLI
- SDK
- REST API
- MCP
reports download generates the report first when necessary:Next Steps
SDK Setup
Configure the Python client and credential resolution.
MCP Tools
Explore the natural-language tools exposed by the MCP server.
Understand Results
Interpret Trust Scores and investigate failed Probes.
Custom Harnesses
Build Evaluation suites for your Agent’s requirements.