AI & Machine Learning

kopern.ai

Manage AI agents, templates, and prompts.

1 endpoint31 known toolsFirst detected May 13, 2026Last detected September 18, 2026

ENDPOINT 1

https://kopern.ai/api/mcp/server

No auth detected

MCP server metadata

Name: kopern
Version: 2.0.0

Capabilities

toolsprompts

Known tools 31

kopern_list_templates

List all 37 AI agent templates (28 general + 9 vertical/business).

Inferred read-only

kopern_list_agents

List all your Kopern agents (name, description, model, domain, grading score).

Inferred read-only

kopern_grade_prompt

Grade a system prompt against inline test cases.

Inferred read-only

kopern_create_agent

Create a new AI agent with a system prompt, model, and optional skills.

Potential side effects

kopern_get_agent

Get full details of an agent: system prompt, model, skills count, tools count, grading suites count.

Inferred read-only

kopern_update_agent

Update any part of an agent: config, skills, tools, or extensions.

Potential side effects

kopern_delete_agent

Permanently delete an agent and all its data (skills, tools, grading suites, sessions, connectors).

Potential side effects

kopern_deploy_template

Deploy an agent from a template (28 general + 9 vertical).

Inferred read-only

kopern_create_grading_suite

Create a grading suite with test cases on an agent.

Potential side effects

kopern_run_grading

Run a grading suite on an agent.

Inferred read-only

kopern_run_autoresearch

Run AutoTune optimization on an agent.

Inferred read-only

kopern_create_team

Create a multi-agent team.

Potential side effects

kopern_run_team

Execute a multi-agent team on a prompt.

Potential side effects

kopern_connect_widget

Enable the embeddable chat widget for an agent.

Inferred read-only

kopern_connect_telegram

Connect an agent to Telegram via a bot.

Inferred read-only

kopern_connect_whatsapp

Connect an agent to WhatsApp Business.

Inferred read-only

kopern_connect_slack

Connect an agent to Slack.

Potential side effects

kopern_connect_webhook

Create an inbound or outbound webhook for an agent.

Potential side effects

kopern_create_pipeline

Create a multi-step pipeline on an agent.

Potential side effects

kopern_run_pipeline

Execute a pipeline on a prompt.

Potential side effects

kopern_list_sessions

List conversation sessions for an agent.

Inferred read-only

kopern_get_session

Get full details of a session including message events, tool calls, and metrics.

Potential side effects

kopern_manage_memory

Manage an agent's persistent memory.

Inferred read-only

kopern_compliance_report

Generate an EU AI Act compliance report for an agent.

Inferred read-only

kopern_get_grading_results

Get detailed results of a grading run: per-case scores, agent outputs, criteria evaluations, improvement notes.

Inferred read-only

kopern_list_grading_runs

List grading runs for a suite.

Inferred read-only

kopern_connect_email

Connect an agent to Gmail or Outlook for email tools (read_emails, send_email, reply_email).

Potential side effects

kopern_connect_calendar

Connect an agent to Google Calendar or Microsoft Calendar for scheduling tools (list_events, create_event, etc.).

Inferred read-only

kopern_get_usage

Get token usage and cost metrics.

Inferred read-only

kopern_export_agent

Export an agent as a portable JSON object (agent config, skills, tools, extensions, grading suites with cases).

Inferred read-only

kopern_import_agent

Import an agent from a Kopern export JSON.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.kopern]
url = "https://kopern.ai/api/mcp/server"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "kopern": {
      "type": "http",
      "url": "https://kopern.ai/api/mcp/server"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: kopern
Remote MCP URL: https://kopern.ai/api/mcp/server

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "kopern": {
      "url": "https://kopern.ai/api/mcp/server"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "kopern": {
      "type": "http",
      "url": "https://kopern.ai/api/mcp/server"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "kopern",
  "transport": "streamable-http",
  "url": "https://kopern.ai/api/mcp/server"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.