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.

K-Data — Korean Sell-Side Research & Market Data

REMOTE · K-DATA-X402-PRODUCTION.THEBLACK1022.WORKERS.DEV · 2 COMPONENTS

Korean equity research, analyst revisions, kimchi premium and news via x402.

0 this week 73 Trust /100

Last scanned (22 hours ago)

Scores higher than 59% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Finance and Payments

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 Security46
Transport & Reachability100
Schema Quality & AI Usability81
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1760 tokens (~110/item across 16 items; 16 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (11)

  • TLS certificate
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (2)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 8 Oct 26 0
    • Stability: 0.97 → pass security
  • 4 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “kimchi_premium_history” rewrote its description, which is the text the model reads security
    • Tool “kimchi_premium” rewrote its description, which is the text the model reads security
    • Tool “kimchi_premium_stats” rewrote its description, which is the text the model reads security
    • Schema quality: 1461 → 1760 ▼ functional
    • Stability: fail → 0.93 functional
    • New tool “preview_kimchi_premium” functional
    • New tool “preview_premium_coverage” functional
    • New tool “preview_research” functional
    • New tool “preview_research_coverage” functional
    • “kimchi_premium_history” added an optional parameter “before” cosmetic
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 7 Sept 26 0
    • Stability: unverified → fail ▼ security
    • A breaking change shipped without a version bump: still 1.1.0 ▼ security
    • Tool “preview_kimchi_premium” was removed ▼ security
    • Tool “preview_research_coverage” was removed ▼ security
    • Tool “preview_research” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “kimchi_premium_history” rewrote its description, which is the text the model reads security
    • Schema quality: 1678 → 1461 ▲ functional
    • “kimchi_premium_history” dropped the optional parameter “before” cosmetic
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 21 Nov 2026 · Probed https://k-data-x402-production.theblack1022.workers.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=theblack1022.workers.dev CN=WE1,O=Google Trust Services,C=US 29 Sept 2026 28 Dec 2026 ECDSA 256 ECDSA-SHA256 1f2096a64d6235d90e4bc14965f6cb54
SANs: theblack1022.workers.dev, *.theblack1022.workers.dev
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of k-data-x402-production.theblack1022.workers.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
workers.dev. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://k-data-x402-production.theblack1022.workers.dev/mcp Verified 200
http (plaintext) http://k-data-x402-production.theblack1022.workers.dev/mcp Inconclusive 405
MCP tools · 16 exposed · ~1,626 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
crypto_krw_markets ~90

Snapshot of all Upbit KRW crypto markets: top by 24h traded value, top gainers, top losers. Optional ?limit=30 (max 100) for the volume ranking. Costs $0.01 in USDC per call, settled via x402.

NameTypeReqDescription
limitinteger–How many top-volume markets to return (default 30, max 100)

No output schema declared.

No examples provided.

crypto_krw_ticker ~88

Live quote for one Upbit KRW market by ticker symbol (e.g. BTC, ETH, XRP): price, 24h change, 24h high/low, 24h traded value in KRW. Costs $0.005 in USDC per call, settled via x402.

NameTypeReqDescription
tickerstringyesCoin ticker symbol, e.g. BTC

No output schema declared.

No examples provided.

fx_usdkrw ~46

Current USD/KRW exchange rate (ECB reference via Frankfurter, fallback open.er-api.com). Costs $0.005 in USDC per call, settled via x402.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

kimchi_premium ~140

Kimchi premium on two bases: premium_official_pct (official USD/KRW rate — the quoted figure) and premium_usdt_pct (Upbit KRW/USDT rate — a gross spot-price comparison using KRW/USDT conversion, before spreads, fees, liquidity and transfer constraints). The two frequently disagree in sign. Optional ?symbols=BTC,ETH (max 10). Costs $0.03 in USDC per call, settled via x402.

NameTypeReqDescription
symbolsstring–Comma-separated coin tickers, e.g. BTC,ETH,XRP. Default: BTC,ETH,XRP,SOL,DOGE

No output schema declared.

No examples provided.

kimchi_premium_history ~201

Time series of the kimchi premium from the recorded archive, both bases, newest-last. Params: ?symbol=BTC &window=1h|6h|24h|7d|30d|90d &points=500 (max 2000) &before=<next_before>. Each page is a separate paid request. Continue while has_more is true using next_before. Inspect actual archive depth and freshness through /api/preview/premium-coverage before buying. Costs $0.08 in USDC per call, settled via x402.

NameTypeReqDescription
beforeinteger–Unix-second cursor from next_before; returns older rows strictly before it
pointsinteger–Max points returned (default 500, max 2000)
symbolstring–Archived tickers: BTC, ETH, XRP, SOL, DOGE, USDT
windowstring–Lookback window (default 24h)

No output schema declared.

No examples provided.

kimchi_premium_stats ~180

Where the current kimchi premium sits inside its own recent distribution: percentile, mean, stdev, z-score, min/max/median, and a plain-language read. Answers 'is this premium unusual right now?' in one call. Built from the recorded archive; inspect actual dates and freshness with the free coverage endpoint. Params: ?symbol=BTC &window=1h|6h|24h|7d|30d|90d &basis=usdt|official. Costs $0.12 in USDC per call, settled via x402.

NameTypeReqDescription
basisstring–Which premium basis to analyse (default usdt)
symbolstring–Archived tickers: BTC, ETH, XRP, SOL, DOGE, USDT
windowstring–Lookback window (default 24h)

No output schema declared.

No examples provided.

korea_market_snapshot ~68

One-call Korea briefing: dual-basis kimchi premium + top Upbit KRW markets + USD/KRW + latest economy headlines translated to English. Everything needed for a Korea market read in a single paid request. Costs $0.08 in USDC per call, settled via x402.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

news_headlines ~112

Latest Korean headlines from Yonhap, Maeil Business and Hankyung, deduplicated and newest-first. Titles stay in Korean — use /api/news/headlines/en for English. Optional ?category=top|economy|tech|politics and ?limit=30 (max 100). Costs $0.01 in USDC per call, settled via x402.

NameTypeReqDescription
categorystring–Filter by category
limitinteger–Max items (default 30, max 100)

No output schema declared.

No examples provided.

news_headlines_en ~123

Latest Korean headlines with English translations attached (title_en), from Yonhap, Maeil Business and Hankyung — deduplicated, newest first. Use this instead of the Korean-only route when the consuming agent does not read Korean. Optional ?category=top|economy|tech|politics and ?limit=20 (max 50). Costs $0.05 in USDC per call, settled via x402.

NameTypeReqDescription
categorystring–Filter by category
limitinteger–Max items (default 20, max 50)

No output schema declared.

No examples provided.

preview_kimchi_premium ~37

Free live BTC-only sample of the dual-basis kimchi premium. Use the paid endpoint for up to 10 symbols.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

preview_premium_coverage ~40

Free archive coverage and freshness for each recorded coin. Check sample count, first and latest timestamps, and stale flag before buying premium statistics or history.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

preview_research ~58

Free, date-stamped archive-depth check for one 6-digit KRX ticker. Shows report and brokerage counts, not report content or consensus.

NameTypeReqDescription
tickerstringyes6-digit KRX code, e.g. 005930

No output schema declared.

No examples provided.

preview_research_coverage ~67

Free, date-stamped KRX research coverage. Lists the most-covered tickers with report count, brokerage count, and archive date range; it does not reveal report content.

NameTypeReqDescription
limitinteger–How many tickers to show (default 25, max 50)

No output schema declared.

No examples provided.

research_company_ticker ~112

Every archived Korean brokerage report for one KRX ticker, newest first: target price, rating, brokerage, analyst, the Korean title with its English translation, and a one-line English summary. Params: ?limit=20 (max 50). Costs $0.05 in USDC per call, settled via x402.

NameTypeReqDescription
limitinteger–Max reports (default 20, max 50)
tickerstringyes6-digit KRX code, e.g. 005930

No output schema declared.

No examples provided.

research_consensus_ticker ~155

Analyst consensus for one KRX ticker, built from the archived research history: mean/median/min/max target price across brokerages, the spread between them, the rating distribution, and a revision log of every target-price and rating change each house has made. Consensus uses each house's latest view, so a weekly publisher does not outvote a quarterly one. Params: ?window=30d|90d|180d|365d (default 90d). Costs $0.12 in USDC per call, settled via x402.

NameTypeReqDescription
tickerstringyes6-digit KRX code, e.g. 005930
windowstring–Lookback window (default 90d)

No output schema declared.

No examples provided.

research_latest ~109

Latest Korean brokerage equity research across all covered companies, newest first — company and KRX ticker, target price, rating, brokerage, analyst, and a one-line English summary of each report. Facts and summaries only; the report PDF stays with its publisher and source_url links back to it. Optional ?limit=20 (max 50). Costs $0.02 in USDC per call, settled via x402.

NameTypeReqDescription
limitinteger–Max reports (default 20, max 50)

No output schema declared.

No examples provided.

Install

How do I install the K-Data — Korean Sell-Side Research & Market Data MCP server?

K-Data — Korean Sell-Side Research & Market Data is a hosted endpoint at https://k-data-x402-production.theblack1022.workers.dev/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 · k-data-x402-production.theblack1022.workers.dev

# add to Claude Code
claude mcp add --transport http juh5ng-korea-stock-research-mcp 'https://k-data-x402-production.theblack1022.workers.dev/mcp'
Common questions

What is the K-Data — Korean Sell-Side Research & Market Data MCP server?

K-Data — Korean Sell-Side Research & Market Data is an MCP server listed in the public MCP registry as io.github.juh5ng/korea-stock-research-mcp. Korean equity research, analyst revisions, kimchi premium and news via x402. This page covers its hosted endpoint (https://k-data-x402-production.theblack1022.workers.dev/mcp).

Is the K-Data — Korean Sell-Side Research & Market Data MCP server safe to use?

K-Data — Korean Sell-Side Research & Market Data scores 73 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 K-Data — Korean Sell-Side Research & Market Data MCP server expose?

K-Data — Korean Sell-Side Research & Market Data exposes 16 tools: preview_premium_coverage, preview_research_coverage, preview_research, preview_kimchi_premium, kimchi_premium, and 11 more. Their descriptions and schemas cost roughly 1,626 tokens of context every time the server is loaded.

Does the K-Data — Korean Sell-Side Research & Market Data MCP server require authentication?

No. We connected to K-Data — Korean Sell-Side Research & Market Data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the K-Data — Korean Sell-Side Research & Market Data MCP server still maintained?

K-Data — Korean Sell-Side Research & Market Data is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the K-Data — Korean Sell-Side Research & Market Data MCP server?

VerifyMCP ran 11 checks on K-Data — Korean Sell-Side Research & Market Data, covering TLS certificate, HSTS header, DNSSEC, Transport and 7 more. 2 items could not be completed, a gap on our side rather than a finding about K-Data — Korean Sell-Side Research & Market Data: Authorization and HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.