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.

Delightful's Game Research Starter Pack

REMOTE · GAMES.THISISDELIGHTFUL.COM · SCANNED SEP 24

Where to look for games industry research: 873 sources across ten markets, cited and free.

+3 this week 77 Trust /100
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 Security63
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1487 tokens (~247/item across 6 items; 6 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 Management90
  • Stability observed for 27 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
  • 95% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Delightful's Game Research Starter Pack MCP server?

Delightful's Game Research Starter Pack is a hosted endpoint at https://games.thisisdelightful.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 · games.thisisdelightful.com

# add to Claude Code
claude mcp add --transport http com-thisisdelightful-games-research-starter-pack 'https://games.thisisdelightful.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-thisisdelightful-games-research-starter-pack": {
      "url": "https://games.thisisdelightful.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-thisisdelightful-games-research-starter-pack": {
      "type": "http",
      "url": "https://games.thisisdelightful.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-thisisdelightful-games-research-starter-pack]
url = "https://games.thisisdelightful.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-thisisdelightful-games-research-starter-pack": {
      "type": "remote",
      "url": "https://games.thisisdelightful.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-thisisdelightful-games-research-starter-pack --url 'https://games.thisisdelightful.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-thisisdelightful-games-research-starter-pack:
    url: "https://games.thisisdelightful.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-thisisdelightful-games-research-starter-pack": {
      "Transport": "http",
      "Url": "https://games.thisisdelightful.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-thisisdelightful-games-research-starter-pack -t streamable-http -u 'https://games.thisisdelightful.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-thisisdelightful-games-research-starter-pack": {
      "type": "http",
      "url": "https://games.thisisdelightful.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Sept 26 0
    • Tool “list_trends” rewrote its description, which is the text the model reads security
    • “list_trends” reworded the description of “limit” cosmetic
  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 0
    • Tool “list_trends” rewrote its description, which is the text the model reads security
    • “list_trends” reworded the description of “limit” cosmetic
  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 0
    • Tool “search_sources” rewrote its description, which is the text the model reads security
    • “search_sources” reworded the description of “cost” cosmetic
  • 17 Sept 26 +1
    • Tool “search_sources” rewrote its description, which is the text the model reads security
    • “search_sources” reworded the description of “cost” cosmetic
  • 16 Sept 26 0
    • Tool “search_sources” rewrote its description, which is the text the model reads security
    • “search_sources” reworded the description of “cost” cosmetic
    • “search_sources” reworded the description of “market” 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 24 Sept 2026 · Probed https://games.thisisdelightful.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=games.thisisdelightful.com CN=YE1,O=Let's Encrypt,C=US 24 Aug 2026 22 Nov 2026 ECDSA 256 ECDSA-SHA384 5eb0a8bac7d700e14af4484e4c867dadf33
SANs: games.thisisdelightful.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of games.thisisdelightful.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
thisisdelightful.com. absent 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
Header Value
strict-transport-security max-age=31536000
x-content-type-options nosniff

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://games.thisisdelightful.com/mcp Verified 200
http (plaintext) http://games.thisisdelightful.com/mcp HTTPS enforced 301 https://games.thisisdelightful.com/mcp
MCP tools · 6 exposed · ~1,387 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
get_landscape ~96

The platform and genre maps. 35 platforms — storefronts, consoles, livestreaming and UGC — with who owns each and where its data lives. 30 genres with definitions, subgenres, example games, and the terms actually used in Chinese, Korean and Japanese. Read the genre map before comparing two datasets: the industry has no shared taxonomy and this records where the vendors disagree.

NameTypeReqDescription
kindstringyesWhich map.

No output schema declared.

No examples provided.

get_market ~183

How to research one of 10 games markets, and the profile behind it. It opens with before_you_start, the research notes for that market: which national annuals are paid and what is free, which venues are closed or could not be verified, which figures overlap or are published on a basis that will not compare, what a weekly chart does and does not count. Then known_gaps, what the directory does not hold for that market and where to go instead. Then a sourced narrative built from claims that each carry the link they came from, a market-size figure with the basis it was published on, a player-population figure with the definition of who was counted, and where that market's data lives. Only these ten have profiles — for any other market code, search_sources with a market filter is what exists.

NameTypeReqDescription
codestringyesMarket code.

No output schema declared.

No examples provided.

get_source ~66

Retrieve one source by its slug, with everything recorded about it. Slugs come back from search_sources and are permanent — the same slug names the same source across releases, so it is what to cite.

NameTypeReqDescription
slugstringyesPermanent identifier, e.g. "sensor-tower".

No output schema declared.

No examples provided.

list_trends ~521

The 38 conversations currently moving the games industry, each with what it is, why it matters, the markets it lands in, its stage, how old the row is, and dated further reading on request. A routing map rather than a synthesis: it names arguments and points at where they are happening, and takes no position on any of them. Filter by market, stage, category or a free-text query; every filter narrows the list and none of them orders it. Rows come 14 to a page: page with offset, or name one by slug to read it with its further reading. This is the fastest-decaying data here — every row is dated, and anything older than about six months needs a refresh.

NameTypeReqDescription
categorystring––
include_further_readingboolean–Default false, and true when slug is given. Further reading roughly doubles a row, so at most 10 rows travel with it; ask for a row by slug to read one in full.
limitnumber–Rows per page, default 14, at most 38 without further reading and 10 with it. A page is the next rows in the order described, never the top ones — nothing here is ranked.
marketstring–Trends that reach this market: tagged to it directly, reached through an EU tag, or global. Each row then says which, in market_relevance, and the list comes back closest first. Most trends in games…
offsetnumber–Rows to skip before the first one returned, for paging. Default 0. The note on each page says what to pass for the next.
querystring–Free text, matched against the name, what it is, why it matters, where to follow it, its category and the titles of its further reading. All words must appear. A word filter, not a semantic search: "…
slugstring–One trend by its permanent slug, as a list returns it. Comes back with its further reading unless include_further_reading says otherwise. The other filters are ignored when this is set.
stagestring–Dominant is sustained mainstream coverage for a year or more. Emerging is real and accelerating. Perennial recurs cyclically. Receding was dominant and is cooling, kept so dated coverage is recognisa…

No output schema declared.

No examples provided.

search_sources ~379

Search 923 curated sources on the video games industry: press outlets, trade associations, datasets, analysts, podcasts, books, YouTube channels and communities across 26 markets. Every one was opened and read before it was described, and each result says what it lets you find out, who owns it and what it costs. This answers "where would I look for this?" — it is a directory of sources, not a source of facts, and nothing in it is ranked or scored.

NameTypeReqDescription
coststring–Recorded on 533 of 923 rows — the press outlets and the individual people are not priced, so filtering on this excludes them rather than reporting them as not free.
groupstring–Broad kind of source.
languagestring–The language you would be reading it in.
limitnumber–Rows per page, default 20, maximum 50. A page is the next rows in file order, never the top ones — nothing here is ranked.
marketstring–Market code. US, JP, KR, UK, DE, FR, CN, MENA, IT, CA have full profiles behind them; SEA, Nordics, BR, IN, MX, ES, TR, NL, AU, PL, TW, EU, LATAM, Asia, BE only tag sources. Global means the source c…
mediumstring–What form it takes.
offsetnumber–Rows to skip before the first one returned, for paging. Default 0. The note on each page says what to pass for the next.
querystring–Free text, matched against the name, the description and the owner. All words must appear. Omit to browse a filter instead.

No output schema declared.

No examples provided.

search_techniques ~142

39 search techniques for games research, each with a query you can paste, what it surfaces and why it works. Includes local-language strategies for researching the Japanese, Korean and Chinese markets without reading the language. Use this before searching the open web on a games question — these are the queries that reach material a plain search buries.

NameTypeReqDescription
marketstring–Techniques for this market, plus the ones that apply everywhere.
querystring–Your question in your own words, for example "what are Japanese players saying about a launch". Techniques are ranked by how many of its words they mention, so a whole question works better than one…

No output schema declared.

No examples provided.

Common questions

What is the Delightful's Game Research Starter Pack MCP server?

Delightful's Game Research Starter Pack is an MCP server listed in the public MCP registry as com.thisisdelightful/games-research-starter-pack. Where to look for games industry research: 873 sources across ten markets, cited and free. This page covers its hosted endpoint (https://games.thisisdelightful.com/mcp).

Is the Delightful's Game Research Starter Pack MCP server safe to use?

Delightful's Game Research Starter Pack scores 77 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 Delightful's Game Research Starter Pack MCP server expose?

Delightful's Game Research Starter Pack exposes 6 tools: search_sources, get_source, get_market, list_trends, get_landscape, search_techniques. Their descriptions and schemas cost roughly 1,387 tokens of context every time the server is loaded.

Does the Delightful's Game Research Starter Pack MCP server require authentication?

No. We connected to Delightful's Game Research Starter Pack without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Delightful's Game Research Starter Pack MCP server still maintained?

Delightful's Game Research Starter Pack is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.