Tool components connect external search, databases, HTTP APIs, email sending, document generation, financial queries, and browser automation capabilities to Agents. When building Agents, first understand each tool's purpose and security boundaries.
Tavily is a web search service for LLMs. It is suitable for retrieving general web information, news, and content that needs to be limited to specific domains. Keep queries focused on a single topic and avoid overly long natural-language questions.
The output usually contains search result summaries, titles, links, snippets, and optional image information. `formalized_content` is commonly passed to the Agent to generate answers, while JSON is used by subsequent nodes to read structured fields.
Tavily Extract reads the body content of one or more known URLs. A common workflow is to use Tavily Search to obtain links, then pass those links to this component to extract page content.
The output contains the page body, title, URL, and extraction status. `formalized_content` is commonly used as Agent context, while JSON preserves the structured extraction result for each URL.
The output contains search result titles, links, and summaries. The organized text can be passed to the Agent for summarization, or subsequent nodes can read the link list from JSON.
The output contains titles, links, and summaries returned by DuckDuckGo. It can be used for web material summarization, news lead organization, or subsequent page extraction.
SearXNG is a self-hostable privacy-oriented meta-search engine. This component calls a user-provided SearXNG instance and is suitable for scenarios that need control over retrieval sources or internal search deployment.
The output contains titles, links, summaries, and source information returned by SearXNG. Before use, configure a reachable SearXNG service address and pass the system security checks.
Keenable is a web search API for AI Agents. By default, it supports a public free path without a key. After configuring a key, you can increase the limit and enable low-latency realtime mode.
| mode | string | Node configuration | pro | `pro` for deeper retrieval or `realtime` for low latency. `realtime` requires an API key. |
| top_n | integer | Node configuration | 10 | Maximum number of results. |
| KEENABLE_API_URL | Environment variable | Deployment configuration | `https://api.keenable.ai` | Service API base URL. Production environments must use HTTPS. Local loopback addresses can use HTTP. |
The output contains search entries, summaries, and links returned by Keenable. It can be summarized by the Agent or passed to subsequent retrieval or extraction nodes. Do not set `realtime` for keyless trial runs.
The Wikipedia component searches encyclopedia entries and extracts entry summaries. It is suitable for querying clear entities, concepts, and historical events. Query terms should be as close as possible to the entry title.
The output contains the titles, summaries, and page links of matching entries. It is suitable for generating concept explanations or background descriptions with the Agent.
The GitHub component searches repositories through the GitHub Repository Search API and sorts by popularity by default. It is suitable for finding open-source projects, reference implementations, and technology ecosystems.
#### Parameter Description
| Field | Type | Required | Default Value | Description |
| top_n | integer | Node configuration | 10 | Maximum number of returned repositories. |
#### Configuration Example
| Configuration Item | Example Value |
| --- | --- |
| Query | RAGFlow |
| Top N | 10 |
#### Output Result
The output contains repository, issue, code, or user search entries, usually including names, links, summaries, update times, and other information. The output includes repository names, links, descriptions, and stars.
Google Scholar is used to retrieve papers, dissertations, books, abstracts, and other academic materials. It is suitable for preliminary literature discovery before a research review, but should not replace verification of original texts and citation information.
The output contains academic retrieval entries such as paper titles, authors, abstracts, source links, and citation information. It is suitable for literature reviews or research lead organization.
ArXiv is used to retrieve open preprints across fields such as computer science, mathematics, physics, and quantitative finance. ArXiv papers may not have undergone peer review, so mark their preprint nature when using the results.
The output contains paper titles, authors, abstracts, publication times, categories, and paper links. It can be used by the Agent to generate paper summaries or research comparisons.
PubMed is used to retrieve life science and biomedical literature. The component queries through NCBI E-utilities and returns titles, authors, journals, DOIs, abstracts, and other information.
The output contains medical literature titles, authors, journals, abstracts, publication dates, and PubMed links. It is suitable for medical literature retrieval scenarios.
BGPT retrieves scientific papers and returns structured evidence, including research methods, sample sizes, results, limitations, conflicts of interest, data availability, and falsifiability tips. It is suitable for evaluating scientific claims, not only for finding paper abstracts.
The output contains biomedical knowledge retrieval results and summaries, which can be further summarized, compared, or used to generate research explanations by subsequent Agents.
Execute SQL connects to an external database and executes SQL statements. The result is formatted as text or table content.
To protect system security, the database address must pass server-side security checks. To connect to a local or internal database, first confirm that the deployment environment allows access.
The output contains SQL execution results, field names, and record content. You can pass formatted text to the Agent for explanation, or let subsequent nodes read structured results.
The Yahoo Finance component queries stock quotes, company profiles, historical market data, financial statements, and news through `yfinance`, and outputs the selected content as a Markdown report.
The output contains a financial query report and structured market data, which can be used by subsequent Agents to generate market overviews or indicator explanations.
WenCai is used to screen financial data such as stocks, indices, funds, Hong Kong stocks, U.S. stocks, futures, and other instruments based on natural-language conditions.
The output contains a financial data list that matches the natural-language screening condition. It can be used for displaying stock selection results, subsequent filtering, or Agent explanation.
:::tip NOTE
Before using the WenCai component, confirm that the WenCai query service is available in the current environment. If the service is not enabled, the component will not return real financial data.
The Email component sends HTML emails through SMTP and supports multiple CC addresses. The current version supports recipients, CC recipients, subject, and email body. It does not support adding attachments or BCC recipients through this component.
Although some SMTP fields are displayed as optional in the UI, a valid SMTP service address, sender account, and authentication information must be provided before sending email.
The output contains sending status and error information. `success` being `true` means the email was sent successfully. If sending fails, check the SMTP address, account, password, and recipient.
The HTTP Request component calls external HTTP APIs, allowing business systems, third-party services, or self-built APIs to be connected to Agent workflows.
| Field | Type | Required | Default Value | Description |
| --- | --- | --- | --- | --- |
| url | string | Yes | Empty | API address. Canvas variables can be used. The Python implementation can add `http://` to addresses with missing protocols, while the Go implementation requires `http://` or `https://` explicitly. |
| method | string | Yes | get | Python supports `get`, `post`, and `put`; the Go implementation also supports `DELETE`. |
| headers | string/object | No | Empty | Request headers in JSON object format. Variables can be used in values. |
| variables | array[object] | No | `[]` | Request parameter list. Each item usually contains `key`, `value`, and `ref`. |
| timeout | integer | No | 60 | Request timeout in seconds. The Go default is 30 seconds. |
The output contains response status code, response headers, and response body. Text responses can be passed to the Agent for summarization, while JSON responses can be read by subsequent nodes.
The Document Generator component outputs Markdown content as PDF, DOCX, TXT, Markdown, or HTML files, and stores the generated files in Agent attachment storage.
The output contains generated file attachment information, download links, and file names. Users can preview, download, or pass the file to subsequent nodes for further processing.
Browser is an LLM-driven browser automation component. It can access web pages, perform multi-step operations, read page content, upload source files, and collect downloaded files based on natural-language tasks. It depends on the configured model and the browser automation dependencies in the runtime environment.
| Field | Type | Required | Default Value | Description |
| --- | --- | --- | --- | --- |
| llm_id | string | Yes | Empty | Configured chat model ID used by Browser. The Go path can accept `model_id` as an alias. |
| prompts | string | Yes | `{sys.query}` | Natural-language browser task. Canvas variables are supported. The Go path can accept `prompt` as an alias. |
| max_steps | integer | No | 30 | Maximum number of browser execution steps. Effective in the Python path. The current Go Stagehand path accepts this field but does not use it during execution. |
| headless | boolean | No | true | Whether to run the browser in headless mode. |
| enable_default_extensions | boolean | No | false | Whether to enable default `browser-use` extensions. |
| chromium_sandbox | boolean | No | false | Whether to enable the Chromium sandbox. In Docker root environments, keep this disabled in general. |
| persist_session | boolean | No | true | Whether to reuse the browser user directory for the same node. Effective in the Python path. |
| upload_sources | array/string | No | `[]` | File IDs, URLs, or upstream variable references for the browser task. |
| url | string | No | Empty | Compatibility field accepted by the current Go component. It does not participate in Stagehand execution. |
| timeout | integer | No | 0 | Compatibility field accepted by the current Go component. It does not participate in Stagehand execution. |
The output contains the browser task execution summary, extracted page content, and any generated download file information. Avoid assigning Browser tasks that involve login, payment, or irreversible submissions.
