Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

DataXAPI

REMOTE · API.DATAXAPI.COM

Market data for AI agents: Douyin, Xiaohongshu, TikTok, WeChat, X and 15 more. Pay per call.

Available components

71 Trust /100

Last scanned (20 hours ago)

Scores higher than 57% of remote servers

Reachable. Last reached 4 Nov 2026.

Category News and Social

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability52
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1453 tokens (~290/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
  • Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 93% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 3 Nov 26 70

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Probed https://api.dataxapi.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.dataxapi.com CN=YR1,O=Let's Encrypt,C=US 17 Sept 2026 16 Dec 2026 RSA 2048 SHA256-RSA 575fafd61cec47e81caa51caf8c3083a808
SANs: api.dataxapi.com
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of api.dataxapi.com. — Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
dataxapi.com. present 2371 13 Verified
api.dataxapi.com. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.dataxapi.com/mcp Verified 200
http (plaintext) http://api.dataxapi.com/mcp HTTPS enforced 308 https://api.dataxapi.com/mcp
MCP tools · 5 exposed · ~990 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
account ~139

balance: the balance, this key's budget and spending. receipt: what one call was charged, by its result ID. usage: calls and charges by day or capability. status: which capabilities are up (no key). Free.

NameTypeReqDescription
group_bystring–usage: day, capability, key_id, entry, source, end_user; commas between several
request_idstring–receipt: the result ID
sincestring–usage: from this time, ISO 8601; 30 days back when left out
untilstring–usage: up to this time
whatstringyes–

No output schema declared.

No examples provided.

call ~509

Fetch one page of data from one capability. Charged per call or per item, as `describe` says; an error costs nothing. IDs read platform.resource.action; give only the parameters that capability takes. The first line of the result says how many items, the charge, the balance, and how to get the next page (`cursor`: a new charged call) or the rest of a result cut to about 20 KB (`read_more`: free). Needs an API key.

NameTypeReqDescription
boardstring–Which board
brandstring–Name of the brand asked about
capabilitystringyes–
cursorstring–Cursor returned by the previous page
export_idstring–A video's encrypted ID as a search result gives it, starting with export/; it expires
fieldsarray–Return only these fields
idstring–ID of the first resource in the path
idempotency_keystring–Optional: left out, the server makes a new one. To be able to repeat a call whose answer you did not get, give a new unique value (a UUID) and send the same value again: that returns the first result…
idsarray–Several IDs in one request
includearray–Extra parts to return alongside
keywordstring–The keyword asked about
keywordsarray–Several terms in one request
langstring–Language code
limitinteger–Items per page
max_pricestring–Refuse if the call could cost more US dollars than this: "0.01"
post_idstring–ID of the post it belongs to
published_withinstring–Published within the last period
querystring–Search terms
regionstring–Country or region code
sincestring–Published at or after
sortstring–Sort order
tabstring–Tab as shown on the platform
typestring–Content format
untilstring–Published at or before
urlstring–Link to the object, instead of its ID
usernamestring–Account handle, instead of its ID
viewstring–How much of each item to return; compact when left out
windowstring–Statistics period

No output schema declared.

No examples provided.

describe ~71

The whole contract of 1 to 5 capabilities: parameters, fields returned in each view, paging, price and the most one call can cost, what it cannot give, example calls. Free, no key. Use it before `call` when unsure of the parameters.

NameTypeReqDescription
idsarrayyesCapability IDs

No output schema declared.

No examples provided.

find ~153

Find which capability returns the data you need, when its ID is not obvious from the `call` list. Say the need in plain words, English or Chinese. Returns up to 5, each with its required parameters, price and a ready-made call. Free, no key. When nothing matches on a named platform it lists everything that platform has: pick from it, or tell the user it is not there. Never use another platform's capability instead.

NameTypeReqDescription
categorystring––
platformstring–Only this platform, by ID or name; alone, lists all it has
querystring–e.g. "comments on a douyin video", "小红书笔记详情"

No output schema declared.

No examples provided.

read_more ~118

Read the rest of a result that `call` cut to fit, or the same result in another view. Free: nothing is fetched again; results are kept 24 hours. Needs the API key that made the call.

NameTypeReqDescription
fieldsarray–Return only these fields
offsetinteger–Where to go on, as printed; from the start when left out
result_idstringyesAs `call` printed it
viewstring–How much of each item to return; compact when left out

No output schema declared.

No examples provided.

Install

How do I install the DataXAPI MCP server?

DataXAPI is a hosted endpoint at https://api.dataxapi.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.dataxapi.com

# add to Claude Code
claude mcp add --transport http com-dataxapi-mcp 'https://api.dataxapi.com/mcp'
Common questions

What is the DataXAPI MCP server?

DataXAPI is an MCP server listed in the public MCP registry as com.dataxapi/mcp. Market data for AI agents: Douyin, Xiaohongshu, TikTok, WeChat, X and 15 more. Pay per call. This page covers its hosted endpoint (https://api.dataxapi.com/mcp).

Is the DataXAPI MCP server safe to use?

DataXAPI scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the DataXAPI MCP server expose?

DataXAPI exposes 5 tools: find, describe, call, read_more, account. Their descriptions and schemas cost roughly 990 tokens of context every time the server is loaded.

Does the DataXAPI MCP server require authentication?

No. We connected to DataXAPI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the DataXAPI MCP server still maintained?

DataXAPI is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.