MULTI-APP TOOLKIT
Build with Langfuse + Perplexity
- Multi-app
- One MCP session
- 13 actions
- 2 triggers
- Managed auth
MCP
One MCP session, both toolsets
One session gives your product or agent every Langfuse and Perplexity 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": "langfuse,perplexity",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// One list, both toolsets: Langfuse and Perplexity tools arrive
// together, each keyed by its own app's slug.
// e.g. run Add Feedback:
const result = await mcp.callTool({
name: "langfuse-add-feedback",
arguments: {
projectId: "Trace ID",
objectType: "Object Type",
},
})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 [langfuseTools, perplexityTools] =
await Promise.all([
pd.components.list({ app: "langfuse" }),
pd.components.list({ app: "perplexity" }),
])
// 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=langfuse" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}"
curl "https://api.pipedream.com/v1/connect/{project_id}/components?app=perplexity" \
-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
Langfuse
Connected account
Perplexity
Connected account
TOOLS
Langfuse tools
The Langfuse tools this pairing puts in reach, each one running on your user's own connected account.
Actions
-
Add Feedback
actionAttach user feedback to an existing trace in Langfuse. See the documentation.Writev0.0.3 -
Get Trace by ID
actionRetrieve a trace from Langfuse by its ID. See the documentation.Read-onlyv0.0.1 -
List Observations
actionRetrieve a paginated list of observations from Langfuse with optional filters. See the documentation.Read-onlyv0.0.2 -
List Project ID Options
actionRetrieves available options for the Project ID field.Read-onlyv0.0.2 -
List Scores
actionRetrieve a paginated list of scores from Langfuse with optional filters. See the documentation.Read-onlyv0.0.2 -
List Sessions
actionRetrieve a paginated list of sessions from Langfuse with optional filters. See the documentation.Read-onlyv0.0.1 -
Log Trace
actionLog a new trace in LangFuse with details. See the documentation.Writev0.0.3
TOOLS
Perplexity tools
The Perplexity tools this pairing puts in reach, each one running on your user's own connected account.
Actions
-
Chat Completions
actionGenerates a model's response for the given chat conversation. See the documentationWritev0.0.9 -
Chat Completions (Advanced)
actionGenerates a model's response for the given chat conversation with multi-message support and Perplexity search controls. Docs: https://docs.perplexity.ai/api-reference/chat-completions-postWritev0.0.4 -
Create Contextualized Embeddings
actionGenerates contextualized vector embeddings for grouped text inputs. See the documentationRead-onlyv0.0.2 -
Create Embeddings
actionGenerates vector embeddings for text inputs. See the documentationRead-onlyv0.0.2 -
Create Response (Agent API)
actionCreates a response using the Agent API with presets, third-party models, and tools. See the documentationWritev0.0.2 -
Search
actionPerforms a web search and returns raw, ranked results. See the documentationRead-onlyv0.0.2
Triggers
No Perplexity triggers are available yet.
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
- langfuse,perplexity
- Primary app
- Langfuse (langfuse)
- Second app
- Perplexity (perplexity)
- Authentication
- API key + API key
- Available actions
- 13
- Available triggers
- 2