---
canonical: https://docs.jentic.com/getting-started/quickstart-video/
representation: markdown-alternate
# Canonical page: https://docs.jentic.com/getting-started/quickstart-video/
# This is the Markdown alternate of the page above.
title: "Jentic Quickstart Video Walkthrough (Archived)"
description: >-
  Watch the original Jentic Quickstart video walkthrough, archived for its demo of the
  retired hosted app.jentic.com and jentic-sdks MCP flow now superseded.
---

# Quickstart (video walkthrough) — archived

!!! warning "Deprecated"
    This is the **original** Quickstart, kept only for its demo video. It describes the retired
    hosted `app.jentic.com` platform and the `jentic-sdks` MCP flow, which the video demonstrates —
    these are no longer used. For the current, supported **self-hosted Jentic One** flow, follow the
    up-to-date [Quickstart](quickstart.md).


> Connect your AI agents to real-world APIs in minutes — without per-API glue code or secret sprawl.

Jentic lets your agents **discover**, **load**, and **execute** APIs and workflows by intent (e.g., “send a Discord DM”, “search NYT”, “translate to Star-Wars speak”) with credential injection, access control, and observability — stored secrets are added at execution time, so they never reach the agent or its prompts.

---

<iframe width="100%" style="max-width:820px;border-radius:10px;aspect-ratio:16/9;" src="https://www.youtube.com/embed/iA7zVFPznvA" title="Jentic Quickstart Demo" frameborder="0" allowfullscreen></iframe>

<small>Prefer to watch? The 5-minute walkthrough above mirrors these steps.</small>

---

## Prerequisites

- Python **3.11+**
- A Jentic account (free) for credentials and API keys
- (Optional) An MCP client — Claude Desktop, Windsurf, Cursor, VS Code MCP

---

## 1. Create your account & connect APIs

1. Go to [app.jentic.com/sign-in](https://app.jentic.com/sign-in) and create an account.
2. In **Credentials**, add API secrets (e.g., Discord bot token, NYT API key).
3. Go to **Agents → New Agent**, select APIs/workflows it can access, and **Generate API key**.

> Each key is **scoped** — the agent only sees what you allow.

---

## 2. Choose your path

=== "Remote MCP (Recommended)"
    ### OAuth Authentication (Recommended)
    
    **OAuth is the recommended authentication method** for connecting to the Jentic Remote MCP Server. It provides secure, token-based authentication that's managed by your MCP client.

    **Supported clients:**
    - **[Claude Desktop](../guides/mcp/claude-desktop-remote.md)** — OAuth authentication
    - **[ChatGPT](../guides/mcp/chatgpt.md)** — OAuth authentication
    - **[Windsurf](../guides/mcp/windsurf-remote.md)** — OAuth authentication (also supports API Key)

    **Quick setup:**
    1. Sign in to [app.jentic.com/sign-in](https://app.jentic.com/sign-in)
    2. Create an MCP Configuration set with the integrations you want to use
    3. Connect your MCP client using OAuth (see client-specific guides above)

    ### API Key Authentication
    
    For clients that don't support OAuth, you can use API Key authentication:

    **Supported clients:**
    - **[Cursor](../guides/mcp/cursor-remote.md)** — OAuth or API Key authentication
    - **[Windsurf](../guides/mcp/windsurf-remote.md)** — API Key authentication (also supports OAuth)

    **Quick setup:**
    1. Create a Live Capabilities agent in [app.jentic.com/live](https://app.jentic.com/live)
    2. Generate an Agent API Key
    3. Configure your MCP client with the API Key (see client-specific guides above)

    > See the [Remote MCP guide](../guides/mcp/remote-mcp.md) for detailed instructions.

=== "Local MCP"
    ### Run the MCP server locally
    Requires [uv](https://github.com/astral-sh/uv):
    ```bash
    uvx --from \
      git+https://github.com/jentic/jentic-sdks.git@main#subdirectory=mcp \
      mcp
    ```

    ### Configure your MCP client

    **Claude Desktop** (macOS example):
    ```bash
    mkdir -p "$HOME/Library/Application Support/Claude"
    open -e "$HOME/Library/Application Support/Claude/claude_desktop_config.json"
    ```

    Paste:
    ```json
    {
      "mcpServers": {
        "jentic": {
          "command": "uvx",
          "args": [
            "--from",
            "git+https://github.com/jentic/jentic-sdks.git@main#subdirectory=mcp",
            "mcp"
          ],
          "env": {
            "JENTIC_AGENT_API_KEY": "<your-agent-api-key>"
          }
        }
      }
    }
    ```

    Restart Claude Desktop.  
    (For Windsurf, Cursor, VS Code MCP — use their MCP config file with the same block.)

    > See the [Local MCP guides](../guides/mcp/Local MCP/) for detailed instructions for each client.

    ### Try it
    In your MCP client chat:
    - "Search Jentic for 'recent Figshare AI papers'"
    - "Load execution info for the top result"
    - "Execute it"

=== "Python SDK"
    ### Install
    ```bash
    pip install jentic
    ```

    ### Export your Agent API key
    macOS / Linux:
    ```bash
    export JENTIC_AGENT_API_KEY="<your-agent-api-key>"
    ```
    Windows (PowerShell):
    ```powershell
    setx JENTIC_AGENT_API_KEY "<your-agent-api-key>"
    $env:JENTIC_AGENT_API_KEY="<your-agent-api-key>"  # current session
    ```

    ### First call: search → load → execute
    ```python
    import asyncio
    from jentic import Jentic, SearchRequest, LoadRequest, ExecutionRequest

    async def main():
        client = Jentic()

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

        # 2) Inspect inputs
        details = await client.load(LoadRequest(ids=[entity_id]))
        print("Inputs:", details.tool_info[entity_id].inputs)

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

    asyncio.run(main())
    ```

    > Credentials required by the capability must be present in your Jentic account (Step 1).

    ### (Optional) Generate LLM tool definitions
    ```python
    from jentic.lib.agent_runtime import AgentToolManager

    manager = AgentToolManager(format="anthropic")  # or "openai"
    tools = manager.generate_tool_definitions()     # pass to your LLM
    result = await manager.execute_tool(
        "discord_send_message",
        {"recipient_id": "123", "content": "Hi from tools!"}
    )
    print(result)
    ```

---

## 3. Popular APIs to try

| API                         | Auth?     | Example use                              |
| --------------------------- | --------- | ---------------------------------------- |
| OSF (osf.io)                | None      | Search preprints, list files             |
| Figshare                    | None      | Get article metadata, recent items       |
| Funtranslations – Star Wars | None      | “Translate to Sith”                      |
| BulkSMS                     | Required  | Send an SMS                              |
| Discord                     | Required  | Post messages, react, DMs                |
| New York Times              | Required  | Top stories, article search              |

---

## Troubleshooting

- **401 / Unauthorized** — Check `JENTIC_AGENT_API_KEY` and that the agent is scoped for the API.
- **Missing credentials** — Add them under **Credentials** in the Jentic app.
- **MCP not connecting** — Restart the MCP client after editing its config.
- **Windows path issues** — Confirm you edited the correct config for your client and user.

---

## Next steps

- [Remote MCP (Recommended)](../guides/mcp/remote-mcp.md) — Connect to Jentic via Remote MCP with OAuth or API Key
- [Local MCP](../guides/mcp/Local MCP/vscode.md) — Run MCP server locally (VS Code, Claude Desktop, Windsurf, Cursor)
- [Add API Integrations](../guides/add-api-integration.md)
- [Create Agent Workflows](../guides/create-agent-workflows.md)
- [Arazzo Runner](arazzo-runner.md)
- [Jentic API Search](api-search.md)
