Google Dialogflow ACTION
Detect Intent
Processes a natural language query and returns structured, actionable data as a result, See REST docs and client API
- Action
- Writes data
- API key
- SDK
- MCP
IMPLEMENTATION
Call this tool
Connect a user's Google Dialogflow account once, then configure and run Detect Intent from your backend or agent.
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 result = await pd.actions.run({
id: "google_dialogflow-detect-intent",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
google_dialogflow: { authProvisionId: "apn_xxxxxxx" },
sessionId: "Session ID",
queryParams: "Query Params",
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "google_dialogflow-detect-intent",
"configured_props": {
"google_dialogflow": { "authProvisionId": "apn_xxxxxxx" },
"sessionId": "Session ID",
"queryParams": "Query Params"
}
}'// 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_dialogflow",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "google_dialogflow-detect-intent",
arguments: {
sessionId: "Session ID",
queryParams: "Query Params",
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
sessionId Session ID | string | A unique session ID, ID of the session created when a context created can be used, e.g. acb92b1d-0a8c-4369-a5fa-ddd7954b2b46 Required |
queryParams Query Params | object | Properties of Query Parameters, See client API Optional |
queryInput Query Input | object | Properties of a Query Input, See client API. For example {"text":{"text":"Hi, what are you doing?","languageCode":"en-EN"}} Optional |
outputAudioConfig Output Audio Config | object | Properties of an Output Audio Config, See client API Optional |
outputAudioConfigMask Output Audio Config Mask | object | Properties of a Field Mask, See client API Optional |
inputAudioFile Input Audio File or URL | string | Provide a file URL or a path to a file in the /tmp directory. Optional |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- google_dialogflow-detect-intent
- Version
- 1.0.1
- App
- Google Dialogflow
- Authentication
- API key
- Read-only
- No
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗