# Agentic Search — DataForB2B

> Use natural language to search people or companies. The AI interprets your query and applies filters automatically. See the documentation

- Key: `dataforb2b-agent-search`
- Type: Action (Read-only)
- Version: 0.0.2
- App: DataForB2B (`dataforb2b`) — https://pipedream.com/apps/dataforb2b.md
- This page (HTML): https://pipedream.com/apps/dataforb2b/actions/agent-search
- Hints: read-only · open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/dataforb2b/actions/agent-search/agent-search.mjs

## Description

Use natural language to search people or companies. The AI interprets your query and applies filters automatically. [See the documentation](https://docs.dataforb2b.ai/api-reference/agent-search)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `query` | `string` | Yes | Natural language search query (minimum 3 characters). |
| `category` | `string` | Yes | Whether to search people or companies. |
| `lookalikeUseCase` | `string` | No | Use case context for lookalike search. |
| `count` | `integer` | No | Number of results to return (default: 25, max: 100). |
| `enrichLive` | `boolean` | No | Whether to enrich results with live data (default: true). |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
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 accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_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": "dataforb2b",
      },
    },
  },
)

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

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "dataforb2b-agent-search",
  arguments: {
    query: "Query",
    category: "Category",
  },
})
```

**TypeScript**

```ts
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: "dataforb2b-agent-search",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    dataforb2b: { authProvisionId: "apn_xxxxxxx" },
    query: "Query",
    category: "Category",
  },
})

console.log(result)
```

**cURL**

```bash
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": "dataforb2b-agent-search",
    "configured_props": {
      "dataforb2b": { "authProvisionId": "apn_xxxxxxx" },
      "query": "Query",
      "category": "Category"
    }
  }'
```

---

- App: https://pipedream.com/apps/dataforb2b.md · All apps: https://pipedream.com/apps