AGENT

Jev Agent

Try a preset on this page with your login session. MCP and off-site REST use a personal key. Jev does not replace the agent’s main model, execute tools, or write long-form reasoning.

Try a preset

Pick a workflow, edit the JSON, and inspect the typed result. Sign in from the header to run.

Request endpoint: /api/v1/decisions/tool-guard

Result

The typed result will appear here.

Access key

Create a personal key on /agent/keys. Put it in a local credential store or JEV_API_KEY for MCP and REST. Never put it in a Skill file, project file, or this page. The runner above uses your login session and does not need it.

export JEV_API_KEY="your-jev-api-key"

MCP

Stateless Streamable HTTP at https://www.jevai.org/api/mcp. Use HTTPS www, not http or the apex host. Those redirects turn MCP POST into GET.

[mcp_servers.jev]
url = "https://www.jevai.org/api/mcp"
bearer_token_env_var = "JEV_API_KEY"
tool_timeout_sec = 30

Skills

Skills tell the agent when to call a tool, which fields to send, and how to apply the result. They do not widen permissions and they do not call Jev by themselves.

for skill in jev jev-task-router jev-model-router \
  jev-tool-guard jev-research-guard jev-completion-review; do
  mkdir -p ".agents/skills/$skill"
  curl -fsSL "https://www.jevai.org/skills/$skill/SKILL.md" \
    -o ".agents/skills/$skill/SKILL.md"
done