MCP

Give your agent Langfuse tools

Every Langfuse action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's Langfuse account for each tool call — you store no tokens.

Pipedream Connect

// 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",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Add Feedback:
const result = await mcp.callTool({
  name: "langfuse-add-feedback",
  arguments: {
    projectId: "Trace ID",
    objectType: "Object Type",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "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",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Add Feedback:
        result = await session.call_tool("langfuse-add-feedback", {
            "projectId": "Trace ID",
            "objectType": "Object Type",
        })

MCP guide →

API PROXY

Call the Langfuse API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Langfuse API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.example.com/v1/me",
})

// Any allowed Langfuse endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.example.com/v1/me

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkuZXhhbXBsZS5jb20vdjEvbWU?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run Langfuse actions from your backend

Connect a user's Langfuse account once, then run Add Feedback on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

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: "langfuse-add-feedback",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    langfuse: { authProvisionId: "apn_xxxxxxx" },
    projectId: "Trace ID",
    objectType: "Object Type",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="langfuse-add-feedback",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "langfuse": {"authProvisionId": "apn_xxxxxxx"},
        "projectId": "Trace ID",
        "objectType": "Object Type",
    },
)

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": "langfuse-add-feedback",
    "configured_props": {
      "langfuse": { "authProvisionId": "apn_xxxxxxx" },
      "projectId": "Trace ID",
      "objectType": "Object Type"
    }
  }'