CONNECT APP

Build with wit.ai

Natural Language for Developers

Artificial Intelligence (AI)

API key

Visit wit.ai ↗ Start building

MCP

Give your agent wit.ai tools

Every wit.ai 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 wit.ai 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": "wit_ai",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Add Utterance:
const result = await mcp.callTool({
  name: "wit_ai-add-utterance",
  arguments: {
    text: "Text",
    outOfScope: true,
  },
})

# 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": "wit_ai",
}

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 Utterance:
        result = await session.call_tool("wit_ai-add-utterance", {
            "text": "Text",
            "outOfScope": True,
        })

MCP guide →

API PROXY

Call the wit.ai API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the wit.ai 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.wit.ai/message?v=20170307&q=hello",
})

// Any allowed wit.ai 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.wit.ai/message?v=20170307&q=hello

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkud2l0LmFpL21lc3NhZ2U_dj0yMDE3MDMwNyZxPWhlbGxv?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 wit.ai actions from your backend

Connect a user's wit.ai account once, then run Add Utterance 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: "wit_ai-add-utterance",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    wit_ai: { authProvisionId: "apn_xxxxxxx" },
    text: "Text",
    outOfScope: true,
  },
})

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="wit_ai-add-utterance",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "wit_ai": {"authProvisionId": "apn_xxxxxxx"},
        "text": "Text",
        "outOfScope": True,
    },
)

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": "wit_ai-add-utterance",
    "configured_props": {
      "wit_ai": { "authProvisionId": "apn_xxxxxxx" },
      "text": "Text",
      "outOfScope": true
    }
  }'