Jentic MCP server for AI agents

Jentic MCP Server provides AI agents with the ability to discover and use external APIs and workflows without writing API-specific code. The server exposes Jentic's capabilities through the Model Context Protocol (MCP), making them accessible to any MCP-compatible client like Windsurf, Claude Desktop, or Cursor.

Installation

Prerequisites

Before installing the Jentic MCP server, you'll need:

Python installed on your system
A Jentic Agent API Key

Getting Your API Key

Visit app.jentic.com/sign-in to create an agent and copy your API key
Set the API key as an environment variable:

export JENTIC_AGENT_API_KEY=<your-agent-api-key>

Installing the MCP Server

The Jentic MCP server can be installed and run using uvx:

uvx --from git+https://github.com/jentic/jentic-sdks.git@main#subdirectory=mcp mcp

This command will install and launch the MCP server.

Usage

Configuring MCP Clients

After installing and running the Jentic MCP server, you'll need to configure your MCP-compatible client to connect to it.

The server will be running locally, and you'll need to point your MCP client to its address.

Using the SDK Directly (Alternative)

If you prefer to use Jentic directly in Python code rather than through the MCP server, you can install the SDK:

pip install jentic

Basic SDK Usage Example

Here's how to use the Jentic SDK in Python:

import asyncio
from jentic import Jentic, SearchRequest, LoadRequest, ExecutionRequest

async def main():
    client = Jentic()

    # 1. Find a capability
    results = await client.search(SearchRequest(query="send a Discord DM"))
    entity_id = results.results[0].id  # op_... or wf_...

    # 2. Load details (inspect schemas / auth, see inputs for operations)
    resp = await client.load(LoadRequest(ids=[entity_id]))
    inputs = resp.tool_info[entity_id].inputs
    print(inputs)

    # 3. Run it
    result = await client.execute(
        ExecutionRequest(id=entity_id, inputs={"recipient_id": "123", "content": "Hello!"})
    )
    print(result)

asyncio.run(main())

Integrating with LLM Agents

For integration with language models like Anthropic or OpenAI, you can use the runtime helpers:

from jentic.lib.agent_runtime import AgentToolManager

manager = AgentToolManager(format="anthropic")
tools = manager.generate_tool_definitions()        # pass these to the LLM
result = await manager.execute_tool("discord_send_message",
                                   {"recipient_id": "123", "content": "Hi"})
print(result)

Troubleshooting

If you encounter issues:

Verify that your JENTIC_AGENT_API_KEY is set correctly
Ensure the MCP server is running before trying to connect with a client
Check that your MCP client is properly configured to connect to the server

For more detailed information and advanced configuration options, refer to the official Jentic documentation.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "jentic" '{"command":"uvx","args":["--from","git+https://github.com/jentic/jentic-tools.git@main#subdirectory=mcp","mcp"],"env":{"JENTIC_UUID":"<your-jentic-uuid>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "jentic": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/jentic/jentic-tools.git@main#subdirectory=mcp",
                "mcp"
            ],
            "env": {
                "JENTIC_UUID": "<your-jentic-uuid>"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "jentic": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/jentic/jentic-tools.git@main#subdirectory=mcp",
                "mcp"
            ],
            "env": {
                "JENTIC_UUID": "<your-jentic-uuid>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect