> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tenderly.co/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server Quickstart

> Connect the Tenderly MCP Server to Claude Code, Claude.ai, Claude Desktop, and other MCP clients.

Get the Tenderly MCP Server running in your AI assistant in under a minute.

## Prerequisites

* A [Tenderly account](https://dashboard.tenderly.co/register)
* At least one Tenderly project

## Connect to the MCP Server

<Tabs>
  <Tab title="Shell">
    Run the following command in your terminal:

    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    claude mcp add tenderly --transport http https://mcp.tenderly.co/mcp
    ```

    Verify the server is connected:

    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    claude mcp list
    ```

    Run `/mcp` inside Claude Code, select **tenderly**, and follow the browser login to authenticate.
  </Tab>

  <Tab title="1. Open [claude.ai](https://claude.ai) a">
    1. Open [claude.ai](https://claude.ai) and go to **Settings → Connectors**.
    2. Click **Add custom connector** at the bottom.
    3. Enter the URL: `https://mcp.tenderly.co/mcp`
    4. Click **Add** and complete the OAuth login.

    Once connected, Tenderly tools are available in any conversation.

    > **Note:** Custom connectors require a Pro or higher Claude plan. On Enterprise plans, only workspace admins can add connectors.
  </Tab>

  <Tab title="1. Open Claude Desktop and go to Setting">
    1. Open Claude Desktop and go to **Settings → Connectors**.
    2. Click **Add custom connector**.
    3. Enter the URL: `https://mcp.tenderly.co/mcp`
    4. Click **Add** and complete the OAuth login.

    > **Note:** Custom connectors require a Pro or higher Claude plan. On Enterprise plans, only workspace admins can add connectors.
  </Tab>

  <Tab title="JSON">
    Add the following to your MCP configuration file (`.cursor/mcp.json`, `.vscode/mcp.json`, or equivalent):

    ```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    {
      "mcpServers": {
        "tenderly": {
          "type": "streamable-http",
          "url": "https://mcp.tenderly.co/mcp"
        }
      }
    }
    ```

    Your editor will prompt you to authenticate when you first use a Tenderly tool.
  </Tab>
</Tabs>

## First tool call

Once connected, try a simple prompt to verify everything works:

> "What is my account name and currently active project?"

Claude will call `get_user_info` and returns your account information and the currently active project (if set). If this works, you're all set.

## Set your active project

Most tools require a project context. Set it once per session:

> "Set my active project to my-project under my-account"

Claude will call `set_active_project`. All subsequent tool calls (simulations, Virtual Environments, traces) will use this project.

<Note>
  You can also let Claude figure out the project automatically, just ask it to do something and it will call `list_projects` first if needed.
</Note>

## Troubleshooting

### Authentication fails or the connector won't log in

If the OAuth login loops or errors out, disconnect the Tenderly connector in your Claude client (Settings → Connectors) and re-add it. In Claude Code, run `/mcp`, select **tenderly**, and redo the browser login. Custom connectors on Claude.ai and Claude Desktop require a Pro or higher plan, on Enterprise plans, only workspace admins can add them.

### "No active project" errors

Most tools require a project context. Ask Claude to set one:

> "Set my active project to my-project under my-account"

Or let Claude pick automatically by asking it to list projects first.

### "No active Virtual Environment" errors

Virtual Environment tools operate on the active Virtual Environment. Either create/fork a Virtual Environment (which auto-activates it) or ask Claude to call `set_active_vnet` with an existing Virtual Environment ID.

### Call trace or events are truncated

`get_simulation_call_trace` is capped at 256 entries and `get_simulation_events` at 100. For large transactions, use the [Advanced Trace Navigation](/ai-tools/tools#advanced-trace-navigation) tools: start with `get_trace_stats` for size, then `get_trace_skeleton` to see the tree structure, and `get_call_trace_node`, `get_subtree_events`, or `search_call_trace` to drill into specific parts. For reverts, `find_failures` and `get_error_path` are usually the fastest path to the root cause.

### Claude picks the wrong network, project, or Virtual Environment

Be explicit in the prompt, name the network, project slug, or Virtual Environment. You can also ask Claude to confirm the active context with `get_user_info` before running a task.

### A tool call returns stale or wrong data

Active project and Virtual Environment state is per-session. If you switch projects or Virtual Environments mid-conversation, confirm the active context with `get_user_info` before running follow-up tools.

## Next steps

* [Tools Reference](/ai-tools/tools): See all 59 tools and what they do
* [Examples](/ai-tools/examples): Walkthroughs for common workflows
* [Virtual Environments](/virtual-environments/overview): Learn more about the environments you can create
* [Simulations](/simulations/overview): Understand how transaction simulation works