# Agents @Kopern.ai

Full AI agent lifecycle platform — create, grade, optimize, deploy and orchestrate AI agents from your IDE or terminal.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add kopern/mcp-server

# Browse available tools
npx -y @smithery/cli@latest tool list kopern/mcp-server

# Get full schema for a tool
npx -y @smithery/cli@latest tool get kopern/mcp-server kopern_list_templates

# Call a tool
npx -y @smithery/cli@latest tool call kopern/mcp-server kopern_list_templates '{}'
```

## Direct MCP Connection

Endpoint: `https://kopern.run.tools`

**Required config:**
- `key` (query) — Kopern API key (starts with kpn_). Get yours at https://kopern.ai → Settings → Personal API Key

## Tools (31)

- `kopern_list_templates` — List all 37 AI agent templates (28 general + 9 vertical/business). Returns slug, title, domain, tagline. No LLM cost.
- `kopern_list_agents` — List all your Kopern agents (name, description, model, domain, grading score). No LLM cost.
- `kopern_grade_prompt` — Grade a system prompt against inline test cases. Uses 6 criteria types (output_match, schema_validation, tool_usage, sa…
- `kopern_create_agent` — Create a new AI agent with a system prompt, model, and optional skills. Returns the agentId.
- `kopern_get_agent` — Get full details of an agent: system prompt, model, skills count, tools count, grading suites count.
- `kopern_update_agent` — Update an agent's configuration (name, system prompt, model, builtin tools, etc.).
- `kopern_delete_agent` — Permanently delete an agent and all its data (skills, tools, grading suites, sessions, connectors).
- `kopern_deploy_template` — Deploy an agent from a template (28 general + 9 vertical). Creates agent + skills + tools + grading suite in one shot. …
- `kopern_create_grading_suite` — Create a grading suite with test cases on an agent. Each case has an input prompt and expected behavior for evaluation.
- `kopern_run_grading` — Run a grading suite on an agent. Executes all test cases, evaluates with configured criteria, returns detailed scores. …
- `kopern_run_autoresearch` — Run AutoTune optimization on an agent. Iteratively mutates the system prompt, re-grades, and keeps improvements. Return…
- `kopern_create_team` — Create a multi-agent team. Agents work together in parallel, sequential (chain), or conditional (router) mode.
- `kopern_run_team` — Execute a multi-agent team on a prompt. Returns each agent's output and the final combined result. Uses YOUR API keys.
- `kopern_connect_widget` — Enable the embeddable chat widget for an agent. Returns the <script> embed code for your website.
- `kopern_connect_telegram` — Connect an agent to Telegram via a bot. Requires a bot token from @BotFather.
- `kopern_connect_whatsapp` — Connect an agent to WhatsApp Business. Requires Meta Cloud API credentials.
- `kopern_connect_slack` — Connect an agent to Slack. Returns an OAuth install URL to authorize in your browser (Slack requires interactive OAuth).
- `kopern_connect_webhook` — Create an inbound or outbound webhook for an agent. Inbound: receive messages via HTTP POST. Outbound: send events to y…
- `kopern_create_pipeline` — Create a multi-step pipeline on an agent. Steps chain agents sequentially with configurable input mapping.
- `kopern_run_pipeline` — Execute a pipeline on a prompt. Steps run sequentially, each feeding its output to the next. Uses YOUR API keys.
- `kopern_list_sessions` — List conversation sessions for an agent. Shows purpose, source, token usage, cost, timestamps. No LLM cost.
- `kopern_get_session` — Get full details of a session including message events, tool calls, and metrics. No LLM cost.
- `kopern_manage_memory` — Manage an agent's persistent memory. Actions: remember (save key-value), recall (search by query), forget (delete by ke…
- `kopern_compliance_report` — Generate an EU AI Act compliance report for an agent. Checks Art. 6 (risk), Art. 12 (audit trail), Art. 14 (human overs…
- `kopern_get_grading_results` — Get detailed results of a grading run: per-case scores, agent outputs, criteria evaluations, improvement notes. No LLM …
- `kopern_list_grading_runs` — List grading runs for a suite. Shows score history, pass rates, and versions over time. No LLM cost.
- `kopern_connect_email` — Connect an agent to Gmail or Outlook for email tools (read_emails, send_email, reply_email). Requires OAuth in browser.…
- `kopern_connect_calendar` — Connect an agent to Google Calendar or Microsoft Calendar for scheduling tools (list_events, create_event, etc.). Requi…
- `kopern_get_usage` — Get token usage and cost metrics. Shows input/output tokens, cost, grading runs, and per-agent breakdown. No LLM cost.
- `kopern_export_agent` — Export an agent as a portable JSON object (agent config, skills, tools, extensions, grading suites with cases). Use kop…
- `kopern_import_agent` — Import an agent from a Kopern export JSON. Creates a new agent with all skills, tools, extensions, and grading suites. …

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get kopern/mcp-server <tool-name>
```

## Prompts (3)

- `create-agent` (use_case) — Step-by-step guide to create, configure and deploy a new AI agent on Kopern
- `grade-and-improve` (agent_id) — Create a grading suite, run evaluation, and optimize an existing agent with AutoResearch
- `deploy-everywhere` (agent_id) — Deploy an agent to all available channels: widget, Slack, Telegram, WhatsApp, webhooks