CONNECT APP

Build with Needle

The Knowledge Threading Platform

Artificial Intelligence (AI)

API key

Visit Needle ↗ Start building

MCP

Give your agent Needle tools

Every Needle 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 Needle 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": "needle",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Search Collection:
const result = await mcp.callTool({
  name: "needle-search-collection",
  arguments: {
    collectionId: "Collection ID",
    text: "Search Query",
  },
})

# 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": "needle",
}

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 Search Collection:
        result = await session.call_tool("needle-search-collection", {
            "collectionId": "Collection ID",
            "text": "Search Query",
        })

MCP guide →

API PROXY

Call the Needle API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Needle 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://needle-ai.com/api/v1/collections",
})

// Any allowed Needle 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://needle-ai.com/api/v1/collections

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9uZWVkbGUtYWkuY29tL2FwaS92MS9jb2xsZWN0aW9ucw?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 Needle actions from your backend

Connect a user's Needle account once, then run Search Collection 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: "needle-search-collection",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    needle: { authProvisionId: "apn_xxxxxxx" },
    collectionId: "Collection ID",
    text: "Search Query",
  },
})

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="needle-search-collection",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "needle": {"authProvisionId": "apn_xxxxxxx"},
        "collectionId": "Collection ID",
        "text": "Search Query",
    },
)

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": "needle-search-collection",
    "configured_props": {
      "needle": { "authProvisionId": "apn_xxxxxxx" },
      "collectionId": "Collection ID",
      "text": "Search Query"
    }
  }'