Internamaro Apify Data MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | Yes | Your own Apify API token. Runs are billed to this account. The server starts and lists its tools without it. | |
| APIFY_MAX_TOTAL_CHARGE_USD | No | Upper limit per tool call in USD. | 1 |
| APIFY_MCP_MAX_RESPONSE_CHARS | No | Longer JSON results are cut to this many characters. The full result stays in the run's dataset in Apify Console. | 200000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Data tools backed by Apify Actors published by ucchiii. Each tool call starts one Actor run on the Apify account that owns APIFY_TOKEN and is billed there at the Actor pay-per-event price.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| html_to_markdownA | Returns one item per input page or HTML string with URL, title, markdown, wordCount, charCount, truncated, status and error. Converts web pages (fetched by URL, no crawling), raw HTML strings or HTML stored in an Apify dataset into clean Markdown for LLMs and RAG, with main-content extraction, GitHub-flavored tables and absolute links. Give at least one of: urls or htmlStrings or datasetId. Runs the Apify Actor ucchiii/html-to-markdown on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/html-to-markdown. |
| bulk_http_requestA | Returns one item per request with URL, method, status code, selected response headers, JSON or text body, timing and error. Sends many HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD with your headers and body) in parallel with retries. Requests to internal or private addresses are blocked. Give at least one of: requests or urls. Runs the Apify Actor ucchiii/bulk-http-request on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/bulk-http-request. |
| flatten_jsonA | Returns one flat item per input item: nested keys become columns like address.city, ready for CSV or a spreadsheet. Flattens nested JSON from pasted items, a JSON/NDJSON URL or an Apify dataset. You choose the key separator, how arrays are written and how deep to flatten. Give at least one of: items or jsonUrl or datasetId. Runs the Apify Actor ucchiii/flatten-json on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/flatten-json. |
| filter_rowsA | Returns every row that matches the conditions, with all its original columns. Filters rows of a CSV, TSV, JSON or NDJSON file (by public URL) or an Apify dataset with simple conditions such as 'country = US' or 'price > 100'. Give at least one of: fileUrl or datasetId. Runs the Apify Actor ucchiii/filter-rows on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/filter-rows. |
| remove_duplicatesA | Returns the merged items with duplicates removed (or only the removed duplicates when output is 'duplicatesOnly'). Merges one or more Apify datasets and removes duplicate rows by the fields you choose (for example url, placeId or email), with case, whitespace and URL normalization. Give at least one of: datasetIds. Runs the Apify Actor ucchiii/dataset-dedup-merge on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/dataset-dedup-merge. |
| excel_to_jsonB | Returns one JSON item per spreadsheet row (numbers and dates kept). For a JSON/NDJSON file it returns one item with a download link to the new .xlsx file. Reads an Excel .xlsx file from a public URL (one sheet or all sheets, any header row) and turns its rows into JSON. A JSON or NDJSON file goes the other way, into an Excel sheet. Give at least one of: fileUrl. Runs the Apify Actor ucchiii/excel-to-json on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/excel-to-json. |
| check_domain_availabilityA | Returns one item per domain with domain, available (true, false or null when unknown), status, tld, checkedAt and error; registrar and dates too when details is true. Checks whether domain names are registered or available, using RDAP registry data and DNS. Up to 1,000 names per call. Do not use it to register other people's trademarks. Give at least one of: domains. Runs the Apify Actor ucchiii/domain-availability-api on YOUR Apify account (APIFY_TOKEN); you pay that Actor's pay-per-event price, see https://apify.com/ucchiii/domain-availability-api. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a clearly distinct operation: HTML→Markdown conversion, parallel HTTP requests, JSON flattening, row filtering, dataset dedup/merge, Excel↔JSON conversion, and domain availability checks. Despite several tools being 'data transformation' utilities, their input types and outputs are described precisely enough that an agent can pick the right one without guessing.
All names use consistent snake_case, which is good. However, several names are noun_to_noun conversions (html_to_markdown, excel_to_json) while others are verb_noun (flatten_json, filter_rows, remove_duplicates, check_domain_availability), so the pattern is not strictly uniform even though it remains readable.
Seven tools is a well-scoped size for a data-wrangling utility server, and each tool covers a genuinely different operation with no filler. Nothing feels padded or missing at the count level.
The surface is a loosely related set of independent utilities rather than a full lifecycle; there is no way to create/write datasets, aggregate or join data, or perform the scraping/crawling that Apify is typically used for. Core transformations (fetch, convert, flatten, filter, dedup, check domains) are covered, but an agent hitting a need outside that short list has no fallback.