Toriigate MCP server
Which MCP servers are Toriigate'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 namedev.toriigate/food-dbverified in the MCP registry
The registry name sits under toriigate.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-26
- Tools2
- Server calls itselftoriigate/food-db
- Server version0.2.0
- Protocol version2025-06-18
On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 59 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "Resolve colloquial Japanese food names to nutrition facts per 100g", the likely first call is search_food.
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 score82 of 100answers 100 · definitions 83 · context 100 · use 0 · connects 100
- Answered100% of days9 of 9 daily checks
- Median first answer277 ms
- Space in an agent's context≈ 219 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 2 of 2
What an agent can do with it
- can do · Resolve colloquial Japanese food names to nutrition facts per 100g
- not sure · Look up Japanese foods missing from USDA or Open Food Facts
- not sure · Attach official source citations to nutrition answers returned to agents
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_foodSearch Japanese foods by name (Japanese or romaji-free text). Returns candidates with nutrition per 100g, source, and disclaimer.
get_nutritionGet nutrition facts per 100g for a food ID returned by search_food.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"food-db": {
"type": "http",
"url": "https://toriigate.dev/mcp/food-db"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http toriigate https://toriigate.dev/mcp/food-dbclaude.ai, ChatGPT and other clients: add https://toriigate.dev/mcp/food-db 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.
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.