
HALDATA - MCP server
Which MCP servers are HALDATA -'s own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-26
- Registry namenet.haldata/mcp-dirverified in the MCP registry
The registry name sits under haldata.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools5
- Server calls itselfmcp-dir
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 186 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer234 ms
- Space in an agent's context≈ 323 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 5 of 5
What an agent can do with it
- not sure · Analyze voice-of-customer feedback trends
- cannot · Query trend data from ChatGPT or Claude via MCP
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_mcpmcp-dir に掲載されているMCPサーバーを、やりたいこと・ツール名・用途から探す(日本語)。例:「在庫を見たい」「GA4」「レビューを分析したい」。query を空にして category だけ指定すると、そのカテゴリの一覧を検索需要順に返す。
get_mcp掲載欄1件の詳細(提供元・認証・権限・接続の難しさ・料金・注意点・安全面・リンク)を slug で取る。
list_categoriesmcp-dir のカテゴリ一覧(key・名前・範囲・掲載数)と「目的から探す」タイルの一覧。
search_recipes複数のMCPを組み合わせて業務を1つ終わらせる手順(レシピ)を探す。例:「離脱の多い商品ページを直したい」「週次レポートを自動化」。query を空にすると全件を返す。
get_recipeレシピ1件の詳細(手順・そのまま使えるプロンプト・出力例)を slug で取る。
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"mcp-dir": {
"type": "http",
"url": "https://mcp-dir-search-bqaj3tfejq-an.a.run.app/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http haldata https://mcp-dir-search-bqaj3tfejq-an.a.run.app/mcpclaude.ai, ChatGPT and other clients: add https://mcp-dir-search-bqaj3tfejq-an.a.run.app/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.