For AI

View as Markdown Open in ChatGPT Open in Claude

Use DataXAPI in Cherry Studio: the MCP server in 4 fields

Give Cherry Studio public data from 21 platforms. Fill in 4 fields once: 5 tools, 207 endpoints, from $0.0003 a call, and a failed call is never charged.

MCP addresshttps://api.dataxapi.com/mcp

A remote address: nothing to deploy, no platform account to sign in to
Give the key a daily and a monthly spending limit; your AI cannot go past it
Every call is in the console's call log, its source marked MCP

The address Cherry Studio connects to: One address and one header: your API key as a bearer token.

Cherry Studioconnected to DataXAPI

List the DataXAPI tools.

DataXAPI is connected with 5 tools: find finds the endpoint for a question, describe shows its parameters and price, call runs it (the only one that is charged), read_more re-reads a result for 24 hours, and account shows your balance. The catalog has 207 endpoints on 21 platforms.

0 calls charged$0.0000

Check it works. Ask it to list the tools. This is the reply to expect; none of it costs anything.

Setup: 4 fieldstyped into the client once
Where it is kept: In the clientthe client keeps the key you type in
Tools: 5 toolsonly call is charged
Transport: Streamable HTTPone address, one header

Connected in three steps

No code to write

Sign up and get a key

Sign in with a 6-digit code sent to your email, or with Google. Free trial on sign-up: up to 333 calls at $0.0003. No card.

dx_…shown in full once, when it is made

Send this to your AI

It reads the setup page and connects the MCP server itself. Put your own key where it says dx_….

Read https://dataxapi.com/agents.md and set up DataXAPI in this agent. My API key is dx_…; use it for every DataXAPI call.

Just ask

Your AI finds the endpoint with find, runs it with call and answers with links. Every call is in the console's call log.

“What has @nasa posted on TikTok lately?”

Set it up

Three steps inside Cherry Studio. Written from the client's own documentation.

Endpoint: https://api.dataxapi.com/mcp
Header: Authorization: Bearer dx_…
Transport: Streamable HTTP
Authentication: API key, as a bearer token
Server: api.dataxapi.com/mcp

What an agent reads to set itself up →

Cherry StudioSettings → MCP Servers → Add Server

Open the place MCP servers are added

Settings → MCP Servers → Add Server

Fill in the fields

Each as written here. The key is typed into the client and kept by it.

FieldValue

Namedataxapi

TypeStreamable HTTP

URLhttps://api.dataxapi.com/mcp

HeadersOne header: Authorization, with the value Bearer, a space, and your API key

Save, then ask it to list the tools

You should get the five below.

Claude Code1 command · ~/.claude.json

Put your key in the environment

Claude Code reads it from there. Add the line to your shell profile to keep it.

export DATAXAPI_API_KEY="dx_…"

Add the server

One command, or the same entry written into ~/.claude.json.

Command~/.claude.json

dataxapi setup --client claude-code

{
  "mcpServers": {
    "dataxapi": {
      "type": "http",
      "url": "https://api.dataxapi.com/mcp",
      "headers": {
        "Authorization": "Bearer ${DATAXAPI_API_KEY}"
      }
    }
  }
}

Restart Claude Code

Then ask it to list the DataXAPI tools. You should get the five below.

5 tools · only call is chargedSetup steps for Claude Code →

Cursor1 command · ~/.cursor/mcp.json

Put your key in the environment

Cursor reads it from there. Add the line to your shell profile to keep it.

export DATAXAPI_API_KEY="dx_…"

Add the server

One command, or the same entry written into ~/.cursor/mcp.json.

Command~/.cursor/mcp.json

dataxapi setup --client cursor

{
  "mcpServers": {
    "dataxapi": {
      "url": "https://api.dataxapi.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:DATAXAPI_API_KEY}"
      }
    }
  }
}

Restart Cursor

Then ask it to list the DataXAPI tools. You should get the five below.

5 tools · only call is chargedSetup steps for Cursor →

Codex1 command · ~/.codex/config.toml

Put your key in the environment

Codex reads it from there. Add the line to your shell profile to keep it.

export DATAXAPI_API_KEY="dx_…"

Add the server

One command, or the same entry written into ~/.codex/config.toml.

Command~/.codex/config.toml

dataxapi setup --client codex

[mcp_servers.dataxapi]
url = "https://api.dataxapi.com/mcp"
bearer_token_env_var = "DATAXAPI_API_KEY"

Restart Codex

Then ask it to list the DataXAPI tools. You should get the five below.

5 tools · only call is chargedSetup steps for Codex →

n8nThe MCP Client Tool node, attached as a tool to an AI Agent node of a workflow

Open the place MCP servers are added

The MCP Client Tool node, attached as a tool to an AI Agent node of a workflow

Fill in the fields

Each as written here. The key is typed into the client and kept by it.

FieldValue

Endpointhttps://api.dataxapi.com/mcp

Server TransportHTTP Streamable

AuthenticationBearer Auth

Credential for Bearer Auth → Bearer Tokenyour API key

Save, then ask it to list the tools

You should get the five below.

5 tools · only call is chargedSetup steps for n8n →

A first conversation

A question, the calls it made, and what each one cost.

Tips for Cherry Studio

Give it its own key. Create a key named “Cherry Studio” with a daily budget in the console. When the budget is used up, calls stop; nothing else on your account is touched.
Let the free tools run without asking. If Cherry Studio asks before it runs a tool, allow find, describe, read_more and account. Leave call on “ask” if you want to approve every charge.
Answers fit the context. A DataXAPI answer stops at about 20 KB on an item boundary and says how to read on; read_more gets the rest at no charge.
Cap what a call may cost. Ask it to pass max_price with every call. A call that could cost more is refused before anything is charged.

Cherry Studioconnected to DataXAPI

What has @nasa posted on TikTok lately?

find{ query: "tiktok account recent videos" }FreeFound tiktok.users.videos.list · TikTok user videos · $0.0020 a call

call{ capability: "tiktok.users.videos.list", username: "nasa", max_price: "0.01" }$0.0020Up to 10 videos · compact view

The latest videos come back in the standard shape, each with its link, text, date and counts. Your AI answers from them, links each video and says what the call cost.

Each post comes back with

url
type
text
lang
published_at
author.name
metrics.likes
metrics.comments
metrics.shares

A call recorded on 2026-10-12 returned 10.

2 tool calls · 1 charged$0.0020

If something is off

What you seeWhyFix

Cherry Studio does not list the DataXAPI toolsCherry Studio was started before the entry was added, or the address is not the one above.Check the entry, then quit Cherry Studio and start it again.

find works, call says unauthorizedThe key did not reach the service from Cherry Studio. The two free tools need no key, so they still answer.Check that the key is where the entry reads it from, and that it starts with dx_. Then restart.

call says insufficient_balance or key_budget_exceededThe balance, or this key's budget, does not cover the price of the call. Nothing was charged.Ask it to run account, then top up or raise the key's budget.