MCP

Give your agent Pinecone tools

Every Pinecone 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 Pinecone 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": "pinecone",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// e.g. run Delete Vectors:
const result = await mcp.callTool({
  name: "pinecone-delete-vectors",
  arguments: {
    indexName: "Index Name",
    prefix: "Prefix",
  },
})

# 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": "pinecone",
}

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 Delete Vectors:
        result = await session.call_tool("pinecone-delete-vectors", {
            "indexName": "Index Name",
            "prefix": "Prefix",
        })

MCP guide →

API PROXY

Call the Pinecone API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the Pinecone 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.pinecone.io/collections",
})

// Any allowed Pinecone 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.pinecone.io/collections

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkucGluZWNvbmUuaW8vY29sbGVjdGlvbnM?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 Pinecone actions from your backend

Connect a user's Pinecone account once, then run Delete Vectors 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: "pinecone-delete-vectors",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    pinecone: { authProvisionId: "apn_xxxxxxx" },
    indexName: "Index Name",
    prefix: "Prefix",
  },
})

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="pinecone-delete-vectors",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "pinecone": {"authProvisionId": "apn_xxxxxxx"},
        "indexName": "Index Name",
        "prefix": "Prefix",
    },
)

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": "pinecone-delete-vectors",
    "configured_props": {
      "pinecone": { "authProvisionId": "apn_xxxxxxx" },
      "indexName": "Index Name",
      "prefix": "Prefix"
    }
  }'