MULTI-APP TOOLKIT
Build with Google Slides + OpenAI (ChatGPT)
- Multi-app
- One MCP session
- 70 actions
- 5 triggers
- Managed auth
MCP
One MCP session, both toolsets
One session gives your product or agent every Google Slides and OpenAI (ChatGPT) tool at once — connect once, list tools, and call them like any single-app session.
// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "google_slides,openai",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// One list, both toolsets: Google Slides and OpenAI (ChatGPT) tools arrive
// together, each keyed by its own app's slug.
// e.g. run Create Image:
const result = await mcp.callTool({
name: "google_slides-create-image",
arguments: {
presentationId: "Presentation",
slideId: "Slide ID",
},
})import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const externalUserId = "{external_user_id}" // any stable ID for this user in your system
const [googleSlidesTools, openaiTools] =
await Promise.all([
pd.components.list({ app: "google_slides" }),
pd.components.list({ app: "openai" }),
])
// One external user owns both connected accounts, so either app's tools
// run on their behalf with the same externalUserId.curl "https://api.pipedream.com/v1/connect/{project_id}/components?app=google_slides" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}"
curl "https://api.pipedream.com/v1/connect/{project_id}/components?app=openai" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}"
# Connect both accounts to the same external_user_id, then
# configure and invoke either app's tools on that user's behalf.ARCHITECTURE
One user, two connected accounts
Your user connects each account once, under whatever ID they already have in your product. The two stay independent — either can be revoked on its own — and your code reaches both through that one user.
Your product
external_user_id
{external_user_id}Pipedream Connect
Managed identity
Auth · tools · routing
Google Slides
Connected account
OpenAI (ChatGPT)
Connected account
TOOLS
Google Slides tools
The Google Slides tools this pairing puts in reach, each one running on your user's own connected account.
Actions top 8 of 24
-
Create Image
actionCreates an image in a slide. See the documentationWritev0.0.8 -
Create Page Element
actionCreate a shape or text box on a slide. Size and position are in points (1/72 of an inch), measured from the top-left of the slide; a default 16:9 slide is 720 x 405 points, so an element placed outside that area is not visible. To add a title or body text, prefer Create Slide withLayoutand the text set, which fills a layout's placeholders instead of positioning boxes by hand. Returns the new element's object ID inreplies[0].createShape.objectId, for use with Insert Text. See the documentationWritev0.0.8 -
Create Presentation
actionCreate a blank presentation or duplicate an existing presentation. See the docs hereWritev0.0.11 -
Create Slide
actionCreate a slide from one of the presentation's layouts and, optionally, fill its title, subtitle and body placeholders in the same request. When building a deck, setLayoutand the text in one call per slide instead of following up with Insert Text: no positioning is needed. Pick a layout that has the placeholders you fill, e.g.TITLE_AND_BODYfor a title and body,TITLEfor a title and subtitle, orTITLE_AND_TWO_COLUMNSfor a title and two bodies; if a placeholder is missing, the error lists the ones the layout has. WithoutLayoutthe slide uses the BLANK layout and cannot take text. Create slides one at a time rather than in parallel. Returns the new slide'sobjectIdand aplaceholdersarray (type,index,objectId,filled) for each title, subtitle and body placeholder, so unfilled ones can be written later with Insert Text. See the documentationWritev0.1.0 -
Create Table
actionCreate a new table in a slide. See the documentationWritev0.0.7 -
Delete Page Element
actionDeletes a page element from a slide. See the documentationWritev0.0.8 -
Delete Slide
actionDeletes a slide from a presentation. See the documentationWritev0.0.8 -
Delete Table Column
actionDelete column from a table. See the documentationWritev0.0.7
TOOLS
OpenAI (ChatGPT) tools
The OpenAI (ChatGPT) tools this pairing puts in reach, each one running on your user's own connected account.
Actions top 8 of 46
-
Chat
actionThe Chat API, using thegpt-3.5-turboorgpt-4model. See the documentationWritev0.3.6 -
Chat using Web Search
actionChat using the web search tool. See the documentationRead-onlyv0.0.10 -
Chat using Functions
actionChat with your models and allow them to invoke functions. Optionally, you can build and invoke workflows as functions. See the documentationWritev0.0.11 -
Chat using File Search
actionChat with your files knowledge base (vector stores). See the documentationRead-onlyv0.0.10 -
Summarize Text
actionSummarizes text using the Chat API. See the documentationRead-onlyv0.1.12 -
Classify Items into Categories
actionClassify items into specific categories using the Chat API. See the documentationRead-onlyv0.1.12 -
Translate Text (Whisper)
actionTranslate text from one language to another using the Chat API. See the documentationRead-onlyv0.1.12 -
Create Transcription
actionTranscribes audio into the input language. See the documentationWritev0.3.6
Triggers
-
New Batch Completed
triggerEmit new event when a new batch is completed in OpenAI. See the documentationv0.0.12 -
New File Created
triggerEmit new event when a new file is created in OpenAI. See the documentationv0.1.2 -
New Fine Tuning Job Created
triggerEmit new event when a new fine-tuning job is created in OpenAI. See the documentationv0.0.17 -
New Run State Changed
triggerEmit new event every time a run changes its status. See the documentationv0.0.13
MULTI-APP
Works with more apps
The combinations customers connect alongside these two — nothing here is limited to a pair.
REFERENCE
Toolkit details
- x-pd-app-slug
- google_slides,openai
- Primary app
- Google Slides (google_slides)
- Second app
- OpenAI (ChatGPT) (openai)
- Authentication
- OAuth + API key
- Available actions
- 70
- Available triggers
- 5