Skip to main content

Documentation Index

Fetch the complete documentation index at: https://pipedream.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

2026-04-15: Tool modes are no longer necessary with the latest Pipedream MCP server (/v3 endpoint). Everything is now essentially tools-only, so the full tool schema is always returned.

​
Tool modes

Pipedream MCP supports a few different methods for interacting with tools:
  1. Sub-agent (default)
  2. Full config
  3. Tools only

​
Sub-agent

When using Pipedream MCP in sub-agent mode, all tools you expose to your LLM take a single input: instruction. The Pipedream MCP server passes the instruction to an LLM to handle the configuration of the main tool using a set of agents with narrowly scoped sets of instructions and additional tools to aid in the configuration and execution of the top-level user prompt.
  • The benefit with this approach is that sub-agent mode abstracts some of the complexity with handling things like remote options and dynamic props, especially for MCP clients that don’t automatically reload tools.
  • However, one downside is that as a developer, you lose some of the control and observability in this model.
While in Beta, Pipedream eats the costs of the LLM tokens in sub-agent mode. We’ll likely pass these costs to developers in the future.
{
  "name": "GOOGLE_SHEETS-ADD-SINGLE-ROW",
  "description": "Add a single row of data to Google Sheets. [See the documentation](https://developers.google.com/sheets/api/reference/rest/v4/spreadsheets.values/append)",
  "inputSchema": {
    "type": "object",
    "properties": {
      "instruction": {
        "type": "string"
      }
    },
    "required": [
      "instruction"
    ],
    "additionalProperties": false,
    "$schema": "http://json-schema.org/draft-07/schema#"
  }
}

​
Full-config

Full-config mode enables support for loading and configuring dynamic props. This mode provides the most flexibility for tool configuration and is required for certain features like automatic app discovery. Use full-config mode when you need:
Your MCP client must be able to reload the list of available tools on each turn. See here for example implementations.

​
Configuring dynamic props

  • Tools that use dynamic props can’t be configured in one shot, as the full prop definition isn’t known until certain inputs are defined.
  • For example, the full set of props for google_sheets-add-single-row aren’t known until you configure the hasHeaders prop. Once you know if there’s a header row, you can retrieve the column names from the header row and make them available as props that can be configured.
  • As you call each tool, you should reload the available tools for the server to expose meta tools for configuration, such as begin_configuration_google_sheets-add-single-row, which causes the rest of the tools to be removed and only expose tools relevant to the configuration.

​
Enabling full-config mode

To use full-config mode, you need to set 2 parameters:
  • Set the toolMode to full-config
  • Pass a conversationId in order to maintain state for your end user’s conversation
const transport = new StreamableHTTPClientTransport(new URL(serverUrl), {
  requestInit: {
    headers: {
      "Authorization": `Bearer ${accessToken}`,
      "x-pd-project-id": PIPEDREAM_PROJECT_ID,
      "x-pd-environment": PIPEDREAM_ENVIRONMENT,
      "x-pd-external-user-id": EXTERNAL_USER_ID,
      "x-pd-app-slug": APP_SLUG,
      "x-pd-tool-mode": "full-config", // Enable full-config mode
      "x-pd-conversation-id": CONVERSATION_ID // Maintain conversation state
    }
  }
});

{
  "name": "google_sheets-add-single-row",
  "description": "Add a single row of data to Google Sheets. [See the documentation](https://developers.google.com/sheets/api/reference/rest/v4/spreadsheets.values/append)",
  "inputSchema": {
    "type": "object",
    "properties": {
      "drive": {
        "anyOf": [
          {
            "anyOf": [
              {
                "not": {}
              },
              {
                "type": "string"
              }
            ]
          },
          {
            "type": "null"
          }
        ],
        "description": "Defaults to `My Drive`. To select a [Shared Drive](https://support.google.com/a/users/answer/9310351) instead, select it from this list.\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: drive"
      },
      "sheetId": {
        "type": "string",
        "description": "Select a spreadsheet or provide a spreadsheet ID\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: sheetId"
      },
      "worksheetId": {
        "type": "string",
        "description": "Select a worksheet or enter a custom expression. When referencing a spreadsheet dynamically, you must provide a custom expression for the worksheet.\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: worksheetId"
      },
      "hasHeaders": {
        "type": "boolean",
        "description": "If the first row of your document has headers, we'll retrieve them to make it easy to enter the value for each column. Note: When using a dynamic reference for the worksheet ID (e.g. `{{steps.foo.$return_value}}`), this setting is ignored."
      }
    },
    "required": [
      "sheetId",
      "worksheetId",
      "hasHeaders"
    ],
    "additionalProperties": false,
    "$schema": "http://json-schema.org/draft-07/schema#"
  }
}

​
Tools-only

To handle all tool configuration and calling directly, you should use tools-only mode.
While some tools will be able to be fully configured and executed in a single shot, not all tools will work in tools-only mode.
{
  "name": "google_sheets-add-single-row",
  "description": "Add a single row of data to Google Sheets. [See the documentation](https://developers.google.com/sheets/api/reference/rest/v4/spreadsheets.values/append)",
  "inputSchema": {
    "type": "object",
    "properties": {
      "drive": {
        "anyOf": [
          {
            "anyOf": [
              {
                "not": {}
              },
              {
                "type": "string"
              }
            ]
          },
          {
            "type": "null"
          }
        ],
        "description": "Defaults to `My Drive`. To select a [Shared Drive](https://support.google.com/a/users/answer/9310351) instead, select it from this list.\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: drive"
      },
      "sheetId": {
        "type": "string",
        "description": "Select a spreadsheet or provide a spreadsheet ID\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: sheetId"
      },
      "worksheetId": {
        "type": "string",
        "description": "Select a worksheet or enter a custom expression. When referencing a spreadsheet dynamically, you must provide a custom expression for the worksheet.\n\nYou can use the \"CONFIGURE_COMPONENT\" tool using these parameters to get the values. key: google_sheets-add-single-row, propName: worksheetId"
      },
      "hasHeaders": {
        "type": "boolean",
        "description": "If the first row of your document has headers, we'll retrieve them to make it easy to enter the value for each column. Note: When using a dynamic reference for the worksheet ID (e.g. `{{steps.foo.$return_value}}`), this setting is ignored."
      }
    },
    "required": [
      "sheetId",
      "worksheetId",
      "hasHeaders"
    ],
    "additionalProperties": false,
    "$schema": "http://json-schema.org/draft-07/schema#"
  }
}

​
Automatic app discovery

Automatic app discovery requires full-config mode, which is not supported on the /v3 MCP server endpoint.
When using earlier versions of the Pipedream MCP server with full-config mode, you can enable Pipedream to automatically identify relevant apps from a given prompt by passing appDiscovery=true.

​
How it works

When app discovery is enabled:
  1. Pipedream analyzes the incoming prompt to identify which apps are most relevant
  2. The initial tool call responds with an array of relevant apps
  3. When the client reloads its available tools, it has tools for the relevant apps

​
App detection examples

User InputApps Detected
”Send a message to the #general channel in Slack”slack
”Create a task in Notion and send a notification to Slack”notion, slack
”Add this email to my spreadsheet”google_sheets, microsoft_excel, airtable_oauth, zoho_sheet, smartsheet
”Schedule a meeting and update my CRM”google_calendar, zoho_crm, hubspot
To search for apps programmatically today, use the app discovery API.