Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vijil.ai/llms.txt

Use this file to discover all available pages before exploring further.

The Vijil MCP server exposes your Console as tools that Claude Code can call directly. Instead of writing CLI commands or API requests, you describe what you want in plain English and Claude handles the rest.
vijil-mcp installs vijil-console as a dependency. You get both the MCP server and the CLI in a single install.

​
Prerequisites

​
Steps

1

Install

Install vijil-mcp:
pip install vijil-mcp
Verify both components are available:
vijil --help
vijil-mcp --help
2

Configure the CLI

vijil-mcp reads its credentials from the same configuration the CLI uses. Point the CLI at your Console API gateway:
vijil auth init --url https://console-api.example.com
Log in with your account credentials:
vijil auth login
You will be prompted for your email and password. The CLI stores your token in ~/.vijil/config.yaml.If you belong to multiple teams, select one:
vijil team list
vijil team use <team_id>
You only need to do this once. vijil-mcp inherits the stored credentials automatically on every start.
3

Connect Claude Code

Create a .mcp.json file in your project root:
{
  "mcpServers": {
    "vijil": {
      "type": "stdio",
      "command": "vijil-mcp"
    }
  }
}
This tells Claude Code to launch vijil-mcp as a local subprocess and discover its tools automatically.
For access across all projects, add the same block to ~/.claude.json instead. Add .mcp.json to your .gitignore if you do not want to commit it, or commit it so your whole team gets the Vijil tools automatically.
4

Verify the Connection

Start Claude Code in the directory containing .mcp.json and ask:

Check my Vijil setup

Claude calls the vijil_status tool, which confirms the CLI is configured, authenticated, and has a team selected. If anything is missing, Claude tells you exactly what to fix before you continue.
5

Register an Agent

Tell Claude about the model you want to evaluate:

Create a new agent called 'My Chat Agent' using gpt-4o at https://api.openai.com/v1/chat/completions with my OpenAI API key sk-…

Claude calls agent_create and shows you the new Agent including its ID. Note that ID — you will use it in the next steps.To see all registered Agents at any time:

List my agents

6

Run an Evaluation

Start a trust evaluation and wait for it to finish:

Run a safety and security evaluation on agent a1b2c3d4-… with a sample size of 50, and wait for it to complete

Claude calls eval_run with wait=True, polls every 5 seconds, and reports back when the evaluation finishes — including the per-Harness scores.
Ask for a sample size of 10 for fast iteration during development. Run the full Harness (~1,250 Probes for security) before releasing to production.
To start an evaluation without waiting, omit the instruction to wait:

Start a safety evaluation on agent a1b2c3d4-…

7

View the Results

Once the evaluation completes, retrieve the full results:

Show me the detailed results for evaluation e5f6a7b8-…

Claude calls eval_results_detail and presents your Trust Score, per-Harness breakdowns, and individual Probe results with identified failure patterns.
8

Generate a Report

Trigger a Trust Report for the completed evaluation:

Generate a report for evaluation e5f6a7b8-…

Claude calls eval_report. Download the Trust Report as HTML or PDF from the Console.

​
What to Ask Next

The Vijil MCP server covers the full evaluation and protection workflow. Here are more things you can ask Claude: Custom Harnesses — generate test suites tailored to your Agent:

Create a custom Harness called 'Support Bot Harness' for agent a1b2c3d4-…

Personas — add realistic user archetypes to shape Probe generation:

Show me the adversarial persona presets

Create a persona from the 'jailbreaker' preset

Policies — define the compliance rules your Agent must follow:

Create a GDPR compliance policy from the preset

Dome Guardrails — configure runtime protection:

Create a default Dome config for agent a1b2c3d4-…

Red Team Campaigns — run adversarial attack sequences:

Run a garak red team campaign against my agent at https://my-agent.example.com/v1 with the purpose 'customer support chatbot'

Trust Dashboard — view aggregated trust metrics:

Show me the trust dashboard

​
Next Steps

MCP Tools Reference

Complete list of all MCP tools with parameters and example prompts

CLI Quickstart

Use the CLI directly for scripted or CI/CD workflows

​
Troubleshooting

SymptomFix
vijil not found in PATHRun pip install vijil-mcp
CLI not configuredRun vijil auth init --url <your-url>
Session expiredRun vijil auth login
No team selectedRun vijil team use <team_id>
Tools do not appear in Claude CodeVerify .mcp.json is in the project root, then restart Claude Code
Claude uses Bash instead of MCP toolsConfirm vijil-mcp is in your PATH: run which vijil-mcp
Last modified on May 19, 2026