> ## Documentation Index
> Fetch the complete documentation index at: https://deepline.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Parallel Search Mcp: Inputs, Cost & CLI Example

> Free, low-latency web search through Parallel's hosted Search MCP. Includes inputs, outputs, pricing notes, Deepline CLI examples, and GTM automation guidance.

## Run in Enrichment Spreadsheet

<Info>
  Use this function as a column step in `deepline enrich`.
</Info>

```bash theme={null}
deepline enrich --input leads.csv --output leads.enriched.csv --with 'result=parallel_search_mcp:{"objective":"{{objective}}","search_queries":"{{search_queries}}"}' --json
```

<Tip>
  Map payload values to spreadsheet columns with `{{column_name}}` placeholders.
</Tip>

## Input Schema

| Name                     | Type     | Required | Default | Description                                                    |
| ------------------------ | -------- | -------- | ------- | -------------------------------------------------------------- |
| `payload.objective`      | `string` | Yes      |         | Required. Search objective for Parallel Search MCP.            |
| `payload.search_queries` | `array`  | Yes      |         | Required. One to three search queries for Parallel Search MCP. |
| `payload.session_id`     | `string` | No       |         |                                                                |
| `payload.model_name`     | `string` | No       |         |                                                                |

<details>
  <summary>Show raw input schema</summary>

  ### Input JSON Schema

  ```json theme={null}
  {
    "type": "object",
    "description": "Parallel Search MCP input.",
    "properties": {
      "objective": {
        "type": "string",
        "description": "Required. Search objective for Parallel Search MCP.",
        "minLength": 1
      },
      "search_queries": {
        "type": "array",
        "description": "Required. One to three search queries for Parallel Search MCP.",
        "minItems": 1,
        "maxItems": 3,
        "items": {
          "type": "string",
          "minLength": 1,
          "maxLength": 100
        }
      },
      "session_id": {
        "type": "string",
        "minLength": 1,
        "maxLength": 100
      },
      "model_name": {
        "type": "string",
        "minLength": 1,
        "maxLength": 100
      }
    },
    "required": [
      "objective",
      "search_queries"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Output Schema

| Name          | Type     | Required | Default | Description                                    |
| ------------- | -------- | -------- | ------- | ---------------------------------------------- |
| `result.data` | `object` | Yes      |         | Provider response payload.                     |
| `result.meta` | `record` | No       |         | Additional response metadata (status, paging). |

<details>
  <summary>Show raw output schema</summary>

  ### Output JSON Schema

  ```json theme={null}
  {
    "type": "object",
    "description": "Parallel Search MCP result payload.",
    "properties": {
      "data": {
        "type": "object",
        "description": "Provider response payload.",
        "properties": {
          "search_id": {
            "type": "string"
          },
          "results": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "url": {
                  "type": "string"
                },
                "title": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "publish_date": {
                  "type": [
                    "string",
                    "null"
                  ]
                },
                "excerpts": {
                  "type": [
                    "array",
                    "null"
                  ],
                  "items": {
                    "type": "string"
                  }
                }
              },
              "required": [
                "url"
              ],
              "additionalProperties": false
            }
          },
          "warnings": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string"
                },
                "message": {
                  "type": "string"
                },
                "detail": {
                  "type": [
                    "object",
                    "null"
                  ],
                  "additionalProperties": {}
                }
              },
              "required": [
                "type",
                "message"
              ],
              "additionalProperties": false
            }
          },
          "session_id": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "required": [
          "search_id",
          "results"
        ],
        "additionalProperties": false
      },
      "meta": {
        "type": "object",
        "description": "Additional response metadata (status, paging).",
        "additionalProperties": {}
      }
    },
    "required": [
      "data"
    ],
    "additionalProperties": false
  }
  ```
</details>

## Advanced: Direct CLI

<Info>
  Use direct execution for single payload debugging.
</Info>

```bash theme={null}
deepline tools execute parallel_search_mcp --payload '{
  "objective": "string",
  "search_queries": "array"
}' --json
```

### CLI flags

| Flag                        | Description                                         |
| --------------------------- | --------------------------------------------------- |
| `--json`                    | Print machine-readable output.                      |
| `--wait`                    | Wait for terminal provider status when supported.   |
| `--debug`                   | Enable wait mode with additional status/log output. |
| `--wait-timeout SECONDS`    | Max seconds to wait in wait mode.                   |
| `--poll-interval SECONDS`   | Polling interval in seconds during wait mode.       |
| `--timeout SECONDS`         | Request timeout in seconds.                         |
| `--connect-timeout SECONDS` | Connection timeout in seconds.                      |

## Provider API Context

<details>
  <summary>Show provider reference (optional)</summary>

  ````md theme={null}
  > Add real-time web search and content extraction to AI agents with the Parallel Search MCP Server The Parallel Search MCP Server provides drop-in web search and content extraction capabilities for any MCP-aware model. The tools invoke the [Search API](/search/search-quickstart) and [Extract API](/extract/extract-quickstart) endpoints but present a simpler interface to ensure effective use by agents. Search runs in [`basic` mode](/search/modes) — tuned for low-latency responses inside agent loops — and total excerpts per tool call are capped to roughly 25,000 characters to stay within typical MCP client output limits. &lt;Tip> **The Search MCP is free to use** — no API key required, great for exploration and light use. For production use cases or higher rate limits, [create a Parallel account](https://platform.parallel.ai) and pass your API key as a Bearer token in the `Authorization` header. &lt;/Tip> The Search MCP comprises two tools: * **`web_search`** — General-purpose web search inside an agent's reasoning loop. Use when the agent needs current information or diverse sources across multiple angles. * **`web_fetch`** — Pulls token-efficient markdown from specific URLs. Use after `web_search` narrows down candidates, or when the agent already has a URL it needs to read in depth. ## One-Click Install Install in any of the following clients with a single click — no API key required. &lt;CardGroup cols={2}> &lt;Card title="Install in Cursor" icon="arrow-pointer" href="https://cursor.com/en/install-mcp?name=Parallel%20Search%20MCP&config=eyJ1cmwiOiJodHRwczovL3NlYXJjaC5wYXJhbGxlbC5haS9tY3AifQ=="> One-click install for Cursor. &lt;/Card> &lt;Card title="Install in VS Code" icon="code" href="https://insiders.vscode.dev/redirect/mcp/install?name=Parallel%20Search%20MCP&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fsearch.parallel.ai%2Fmcp%22%7D"> One-click install for VS Code. &lt;/Card> &lt;Card title="Install in LM Studio" icon="microchip" href="lmstudio://add_mcp?name=Parallel%20Search%20MCP&config=eyJ1cmwiOiJodHRwczovL3NlYXJjaC5wYXJhbGxlbC5haS9tY3AifQ%3D%3D"> One-click install for LM Studio. &lt;/Card> &lt;Card title="Install in Goose" icon="feather" href="goose://extension?url=https%3A%2F%2Fsearch.parallel.ai%2Fmcp&type=streamable_http&timeout=300&id=parallel-search-mcp&name=Parallel%20Search%20MCP&description=Parallel%20Search%20MCP%20server"> One-click install for Goose. &lt;/Card> &lt;/CardGroup> For Claude Code, Codex CLI, Claude Desktop, Windsurf, Zed, Gemini CLI, Warp, Kiro, and other clients, see the [Installation](#installation) section below — those clients use a CLI command or a JSON config file rather than deep-link URLs. ## Use Cases The Search MCP is suited for any application where real-world information is needed as part of an AI agent's reasoning loop. Common use cases include: * Real-time fact checking and verification during conversations * Gathering current information to answer user questions * Researching topics that require recent or live data * Retrieving content from specific URLs to analyze or summarize * Competitive intelligence and market research ## Installation The Search MCP can be installed in any MCP client. Two endpoints are available: * **`https://search.parallel.ai/mcp`** — default. Free to use anonymously at lower rate limits. Pass a Parallel API key as a Bearer token (`Authorization: Bearer &lt;key>`) to unlock higher limits. **OAuth is not advertised on this endpoint**, so clients that support OAuth sign-in (Claude Desktop, Claude.ai custom connectors, Codex, etc.) will not prompt you to log in here — use `/mcp-oauth` below if you prefer OAuth. * **`https://search.parallel.ai/mcp-oauth`** — the OAuth-capable endpoint. Requires authentication: Bearer API key OR the OAuth flow. Anonymous requests return `401`. Use this when you want OAuth instead of managing a Bearer key, or when you need to guarantee every request is attributed to a Parallel account — for example, organization-wide deployments, Zero Data Retention (ZDR) setups, or any context where unauthenticated traffic is not acceptable. Swap `/mcp` for `/mcp-oauth` in any of the config snippets below if you want OAuth or enforced authentication. The Search MCP can also be [used programmatically](/integrations/mcp/programmatic-use) by providing your Parallel API key in the Authorization header as a Bearer token. ### Cursor Add to `~/.cursor/mcp.json` or `.cursor/mcp.json` (project-specific): ```json theme={"system"} { "mcpServers": { "Parallel Search MCP": { "url": "https://search.parallel.ai/mcp" } } } ``` For more details, see the [Cursor MCP documentation](https://cursor.com/docs/context/mcp). *** ### VS Code Create `.vscode/mcp.json` in your workspace (or run the **MCP: Open User Configuration** command for a user-level `mcp.json`): ```json theme={"system"} { "servers": { "Parallel Search MCP": { "type": "http", "url": "https://search.parallel.ai/mcp" } } } ``` For more details, see the [VS Code MCP documentation](https://code.visualstudio.com/docs/copilot/customization/mcp-servers). *** ### Claude Desktop / Claude.ai Go to Settings → Connectors → Add Custom Connector, and fill in: ```text theme={"system"} Name: Parallel Search MCP URL: https://search.parallel.ai/mcp ``` This URL connects anonymously. If you'd rather sign in with OAuth (so Claude manages the token for you), use `https://search.parallel.ai/mcp-oauth` instead — it triggers Claude's OAuth sign-in flow. If you are part of an organization, you may not have access to custom connectors. Contact your organization administrator for assistance. &lt;Tip> **Org admins (Team / Enterprise plans):** to route Claude's web queries through the Parallel Search MCP instead of Claude's built-in web search, disable the native web search tool at [**Admin settings → Capabilities**](https://claude.ai/admin-settings/capabilities). Once off at the workspace level, members cannot re-enable it individually. See the [Claude web search

  &lt;Note>
  Provider reference truncated for page speed. Use the provider's official docs for the full upstream reference.
  &lt;/Note>
  ````
</details>

## Cost

* Pricing model: `fixed` (per call).
* Estimated Deepline credits: `0` per pricing unit.
* Provider-native pricing may still exist outside Deepline credit billing.
* Billing mode: `no_bill`.