Sort

AgentEarth Tool Catalog

Others

208Tools
12tags
22Providers

Use maps, weather, office, document, spreadsheet and messaging capabilities on demand while reducing the cost of fragmented procurement.

  1. Workflows validate parameters automatically and use retries and backup tools to prevent one failed step from disrupting the entire task.
  2. Google Maps, OpenWeather, Firecrawl, DumplingAI, GitHub and other cross-scenario tools are available in one place for enterprise automation, operational collaboration, data processing and end-to-end execution.

Tool List

208 tools

ae_amap_maps_get_v3_geocode_regeo

Convert mainland China GPS coordinates into a structured address and nearby landmarks using Amap (Gaode).

ae_amap_maps_get_v3_assistant_inputtips

Get search suggestions and keyword completions for places, addresses, and transit in mainland China using Amap (Gaode).

ae_elevenlabs_speech_to_text_scribe_v2

Transcribe audio into text with optional speaker labels, language selection, key terms, and sound-event tags. audio_url must point to a supported audio format (.mp3, .wav, .m4a, .ogg, .flac, .aac); extract the audio track first for video files. Audio duration must not exceed 1200 seconds (20 minutes); trim or split longer audio before submitting.

ae_amap_maps_get_v3_config_district

Look up administrative divisions like provinces, cities, and districts. Retrieve area codes (adcodes) and optional boundary coordinates for mapping regions.

ae_serper_places

Search for local businesses and places using Serper to find addresses, phone numbers, coordinates, ratings, and reviews.

ae_amap_maps_get_v5_direction_transit_integrated

Plan bus and metro journeys with Amap (Gaode), including walking connections and transfer legs. Provide origin and destination as GCJ-02 longitude,latitude coordinates (up to six decimal places each), and city1 and city2 citycodes, including for journeys within the same city. If using originpoi or destinationpoi, provide both; both are required for strategy=6. Optional settings include route preferences, alternative count, night services, travel date/time and additional response field groups. Returns business status, result count and transit itineraries, with walking and transport segments and distance, duration or cost details where supplied by Amap. Optional details depend on show_fields and the provider response. Check status="1" and infocode="10000" for business success; HTTP success alone is insufficient.

ae_dumplingai_extract_video

Extract transcripts, frames, and insights from videos using DumplingAI.

ae_serper_maps

Search for local businesses, places, and geographic locations using Serper's Google Maps-style API.

ae_qweather_weather_daily_forecast

Get the 3-day daily weather forecast, including temperature and conditions.

ae_dumplingai_doc_to_text

Extract plain text from PDF, Word, or PowerPoint documents using DumplingAI.

ae_qweather_weather_now

Get current weather conditions, including temperature, wind, humidity, and visibility.

ae_api_sports_football_get_odds

Get pre-match football odds. Specify a target fixture, a date, or a league and season; filtered queries may have no available odds.

ae_firecrawl_parse

Parse one local document into Markdown, HTML, raw HTML, links, a summary, JSON or query answers using Firecrawl. Supported file extensions are .html, .htm, .xhtml, .pdf, .docx, .doc, .odt, .rtf, .xlsx and .xls. Input and workflow • Provide exactly one nonempty string: filePath or uploadRef. In local MCP mode, filePath points to a file on the MCP server filesystem. In hosted mode, filePath refers to the caller's file but is not read or checked by the hosted server: the first call returns upload instructions. After the caller completes the upload, call again with the returned short-lived uploadRef and the desired parsing options. • Hosted mode is a two-call upload handoff, not an asynchronous parse job with status polling. This tool exposes no separate job-status/result retrieval lifecycle. Upload instructions alone are not parsed content. Options • formats: an array of markdown, html, rawHtml, links, summary, json and/or query. For structured extraction, jsonOptions accepts prompt and schema (a JSON schema object). For query answers, queryOptions requires prompt (up to 10000 characters) and mode: directQuote or freeform. Although the schema lists freeform as the default, mode is required when supplying queryOptions. • For PDFs, include parsers:["pdf"]. pdfOptions.maxPages optionally limits parsing to an integer from 1 to 10000 pages. • Hosted phase-one contentType overrides the MIME type; otherwise it is inferred from the file extension without reading the file. declaredSizeBytes is optional and must be an already-known integer size from 1 to 9007199254740991 bytes; this range is not a promise that uploads of that size are accepted. • includeTags and excludeTags select HTML tags; onlyMainContent requests main content only; removeBase64Images removes base64-encoded images from output. • redactPII requests redaction of personal information. zeroDataRetention requests no retention after processing, requires an eligible authenticated account, and should be omitted for anonymous keyless use. • proxy accepts basic or auto only. skipTlsVerification requests skipping TLS certificate verification when retrieving file resources, reducing transport verification. storeInCache is an exposed cache-storage request, not a documented cache guarantee. maxAge is ignored: parse never reuses or stores indexed content. All options other than the filePath/uploadRef choice are optional; extra unsupported properties are not accepted. Returns The response is an object whose fields vary by phase and outcome. Hosted phase one can return mode, upload instructions (uploadUrl, method, headers, fields, command, expiresAt, maxSizeBytes and uploadRef), nextToolCall as {name, arguments}, notes and message. Final data contains parsed content in the requested formats and may include data.metadata.scrapeId. Other possible fields are success, error, warning, raw for a non-JSON response body, agent_hints and conversationId. Fields are not guaranteed to be present, and no fixed mode/status values or fixed inner data layout are specified. Follow the returned upload expiry and maximum size rather than assuming global limits. Limits One file per parse; repeat calls for multiple files. Remote web URLs belong in the separate firecrawl_scrape operation. Interactive actions, screenshots, branding and change tracking are not supported; waitFor, location and mobile are not exposed by this interface. Do not send filePath together with uploadRef. For specific data points, JSON with a schema is appropriate; for complete document text, Markdown is appropriate.

ae_imageutils_rembg

ae_imageutils_rembg — Remove an image background using WaveSpeed's Bria remove-background. Provide the image URL in request_body.image. The image is processed asynchronously, with outputs available when processing completes. No additional processing options are exposed.

ae_douyin_billboard_fetch_content_tag

## Purpose Retrieve content-category tags for building `tags` or `query_tag` filters in compatible queries. ## Input No parameters are required or accepted. Call with `{}`. ## Result The response's `data` payload contains the category-tag information used to identify top-level categories and subcategories. The exact payload structure is not specified. This is tag reference data, not a list of content items or rankings. ## Usage example The documentation illustrates the top-level category “美食” (Food), ID `628`, and its subcategory “品酒教学” (Wine-tasting instruction), ID `62802`. A corresponding filter is `{"value":628,"children":[{"value":62802}]}`. This is an example of a filter for another query, not an input to this tool or a guaranteed response shape. Use the returned tag identifiers when constructing filters.