Server definition

Hash: sha256:e3a709ff437d4bb64c032ded2f0a5f7930590845b05c78fe7f7f8a34a1bfe047
What it is: What a remote MCP server returned when asked what it offers: 5 tools

The blob, as servednamed by its sha256

{
  "instructions": "Additive Atlas: food additive regulations of Japan (JP), the EU and the US, plus Codex/JECFA/IARC/EFSA evaluations, each kept faithful to its own primary source and returned side by side.\nDisclaimer: Every record is a draft and needs verification. This is not a safety judgement: it returns what each jurisdiction has officially decided, the differences between them, and the sources.\nThe tools never judge whether an additive is safe or unsafe and never rank; they return what each jurisdiction has officially decided and the sources. If a question cannot be answered from the returned data, say so and name what would settle it.\nResponse shapes and vocabulary are specified in the OpenAPI document at /openapi.yaml on this host. Free tools return facts from the substance's own axis; the cross-axis derivation (get_substance_diff, analyze_label_diff) is paid and only available over HTTP.",
  "tools": [
    {
      "description": "Find the additives named on a label (same as HTTP POST /v1/labels/analyze). Splits the additive section into tokens and returns, per token, the substances it resolves to (SubstanceSummary: facts on their own axis), plus known interactions between the detected substances.\nCutting the additive section out of the label is the caller's job; sending the whole ingredient section is allowed. Matching is exact against the alias vocabulary in scope: a token with matches: [] is unresolved, which (open world) does not distinguish \"not an additive\" from \"an additive not known here\".\n`axis` and `lang` must be one of the accepted pairs: JP+ja, US+en, EU+nl, EU+fr, EU+de, EU+es, EU+pl, EU+el, EU+bg.\nNot a safety judgement: every record is a draft and needs verification.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "axis": {
            "description": "Regulatory axis the label or name belongs to: JP, EU or US.",
            "type": "string"
          },
          "lang": {
            "description": "Language of the name or label text (ISO 639-1), e.g. ja, en, de, fr.",
            "type": "string"
          },
          "text": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              }
            ],
            "description": "The additive (or whole ingredient) section of one label: one raw string (split at 、 , ， / for Japanese and , ; . : for Latin script, at bracket depth zero; whitespace is not a separator), or an array of already-split items (tokens[i] corresponds to item i)."
          }
        },
        "required": [
          "text",
          "axis",
          "lang"
        ],
        "type": "object"
      },
      "name": "analyze_label",
      "outputSchema": null
    },
    {
      "description": "(Paid; not available through MCP.) Same input as analyze_label, but each detected substance carries the cross-axis derivation.\nThis tool does not return that data: it returns the HTTP endpoint (POST /v1/labels/analyze/diff with the same JSON body, 0.01 USDC per request via x402 on Base) to call instead.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "axis": {
            "description": "Regulatory axis the label or name belongs to: JP, EU or US.",
            "type": "string"
          },
          "lang": {
            "description": "Language of the name or label text (ISO 639-1), e.g. ja, en, de, fr.",
            "type": "string"
          },
          "text": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              }
            ],
            "description": "The additive (or whole ingredient) section of one label: one raw string (split at 、 , ， / for Japanese and , ; . : for Latin script, at bracket depth zero; whitespace is not a separator), or an array of already-split items (tokens[i] corresponds to item i)."
          }
        },
        "required": [
          "text",
          "axis",
          "lang"
        ],
        "type": "object"
      },
      "name": "analyze_label_diff",
      "outputSchema": null
    },
    {
      "description": "One substance with everything its own roster says (same as HTTP GET /v1/substances/{id}): identifiers, category, aliases, translations, the source-ledger row, groups, and — depending on the axis — Japanese use standards, EU/Codex conditions of use, mandatory labelling statements, the roster's definition text or the CFR citation.\nFacts from the substance's own axis only; nothing here crosses an axis (that is get_substance_diff, paid, HTTP only). Axis-specific keys are present only where the roster has that concept, and an empty list means something (use_standards: [] = no use standard; use_conditions: [] = no permitted food category).\nNot a safety judgement: every record is a draft and needs verification.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "id": {
            "description": "Substance id as returned by search_substances or analyze_label, e.g. eu:e951, jp:designated-aspartame, us:cfr-172-804.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_substance",
      "outputSchema": null
    },
    {
      "description": "(Paid; not available through MCP.) For every axis other than the substance's own, what that axis says (with a per-cell source) kept separate from what was derived from it; when nothing can be concluded, a refusal says why and what would settle it.\nThis tool does not return that data: it returns the HTTP endpoint (GET /v1/substances/{id}/diff, 0.01 USDC per request via x402 on Base) to call instead.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "id": {
            "description": "Substance id as returned by search_substances or analyze_label, e.g. eu:e951, jp:designated-aspartame, us:cfr-172-804.",
            "type": "string"
          }
        },
        "required": [
          "id"
        ],
        "type": "object"
      },
      "name": "get_substance_diff",
      "outputSchema": null
    },
    {
      "description": "Look up substances by name on one regulatory axis (same as HTTP GET /v1/substances?name=…).\nThe name is normalised (NFKC, whitespace removed, lower-cased) and matched **exactly** against the names and aliases the axis itself uses in that language (E numbers and official names for EU, 品目名 and label terms for JP, CFR names for US) — no partial or fuzzy matching. The official name is an alias of itself.\nReturns the matching substances (SubstanceSummary: facts from their own roster only) and, per row, what text matched.\n`axis` and `lang` must be one of the accepted pairs: JP+ja, US+en, EU+nl, EU+fr, EU+de, EU+es, EU+pl, EU+el, EU+bg.\nNot a safety judgement: every record is a draft and needs verification.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "properties": {
          "axis": {
            "description": "Regulatory axis the label or name belongs to: JP, EU or US.",
            "type": "string"
          },
          "lang": {
            "description": "Language of the name or label text (ISO 639-1), e.g. ja, en, de, fr.",
            "type": "string"
          },
          "name": {
            "description": "The name to look up, as printed on a label or roster.",
            "type": "string"
          }
        },
        "required": [
          "name",
          "axis",
          "lang"
        ],
        "type": "object"
      },
      "name": "search_substances",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:e3a709ff437d4bb64c032ded2f0a5f7930590845b05c78fe7f7f8a34a1bfe047 | sha256sum