Server definition

Hash: sha256:4746f09c93d3b1b3863ac5ac02f0199c05faace0dfd50313fba165d064adf2cb
What it is: What a remote MCP server returned when asked what it offers: 18 tools

The blob, as servednamed by its sha256

{
  "instructions": "Sniff MCP — agent-callable canine genomics over the Sniff Atlas (open, CC-BY-4.0). Covers 9,667,790 common (MAF>=1%, incl ~3M at 1-5%) canine coding variants across 188 dog breeds on the CanFam4 assembly, with breed-stratified allele frequencies, calibrated ESM2 pathogenicity (AUC 0.935 vs OMIA), Pangolin splice, and Zoonomia phyloP conservation.\n\nIDENTIFIERS: positions are CanFam4 'chrom:pos' (e.g. '5:56189113' or 'CANFAM4:5:56189113' or 'chr5:56189113'). Assembly defaults to canfam4.\nSTART: for a natural-language question ('what is X', 'does breed Y get Z', 'human equivalent of W'), call `ask` — it returns a GROUNDED, CITED answer (or an honest abstain) over the fused knowledge layer (OMIA inherited diseases + dog<->human homolog bridge, AVCG variant pathogenicity grades, carrier risk, longevity, temperament, diversity). For the documented-disease atoms of a breed or disease, call `disease_bridge`. For a single variant, `ask_variant_context` returns frequency + pathogenicity + gene + cross-breed + provenance in one call. Use `variant_search` for filtered discovery, `gene_summary`/`breed_summary` for rollups, `metadata`/`breeds_in_atlas` for discovery.\n\nSAMPLE-SIZE CONFIDENCE: breed-level responses carry n_dogs, an af_ci95 (Wilson interval), and a confidence grade (high/moderate/low/very_low). The atlas is sample-skewed (median ~22 dogs/breed); an af of 0 in a 12-dog breed is NOT 'absent' (its CI may reach 0.10+). ALWAYS weight by confidence — do not report a frequency, a popmax, or a 'breed with the most/least X' claim without its n_dogs/CI.\nRIGOR CONTRACT: every response carries a provenance block (data DOI, evidence grade, citation). Pathogenicity outputs ALWAYS include predicted_disease_relevance='UNPROVEN' — these are computational predictions, NOT clinical diagnoses, and the resource is common-variant only (MAF>=1%). The OMIA disease layer + grounded `ask` are LIVE (cite-or-abstain; carrier != affected; educational, not diagnostic). Always surface the citation and the UNPROVEN caveat to the user.",
  "tools": [
    {
      "description": "Ask Sniff a natural-language canine-genetics question and get a GROUNDED, CITED answer (or an honest\nabstain). Covers inherited diseases (OMIA) and their human homologs (the dog<->human disease bridge),\nbreed disease/carrier risk, variant pathogenicity grades (AVCG; Boeykens et al. 2024, curated in OMIA),\nlongevity/life-expectancy (McMillan 2024), temperament (Darwin's Ark/Morrill 2022, with breed-explains-X%\ncaveats), and genetic diversity. The engine answers ONLY from cited Sniff atoms and returns\n`abstained: true` if it lacks grounded data — it never guesses. Educational, not diagnostic\n(carrier != affected; advise a vet). Returns {answer, citations:[atom_ids], abstained}. USE THIS for any\n'what is X / does breed Y get Z / human equivalent of W' question; use the variant/breed/gene tools for\nstructured lookups by identifier.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "question": {
            "type": "string"
          }
        },
        "required": [
          "question"
        ],
        "type": "object"
      },
      "name": "ask",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "THE INSTRUMENT — ask a free-form CROSS-SPECIES genetics question and get FILTERED, HONEST HINTS (never a\nconfident guess). It compiles your question into a typed query plan over the dog<->human edge-graph, runs it\ndeterministically, and scores each answer PATH by its weakest edge — returning ranked hints with an evidence\nTIER (fact / computational / inferred) + citations, or an honest ABSTAIN with a demand signal when the graph\ncan't answer. BEST FOR model-discovery / translational traversal: 'which dog breeds or genes model human\n<disease>', 'what is the dog ortholog of <gene>', 'what dog disease is phenotypically like <human disease>'.\nAnswers are HYPOTHESIS-GENERATING, not clinical claims: a `fact` hint = an OMIA-curated model-of; a\n`computational` hint = a conserved 1:1 dog ortholog (a candidate — never 'dogs get this disease'); `inferred`\n= shared cross-species phenotype. Returns {plan (what it asked the graph), hints:[{answer, tier, score,\npath (the cited edges), weakest_edge, provenance}], abstain, demand_signal}. Set narrate=true for a gated\none-line prose summary per hint (faithful-or-honest-template; it can never fabricate). Use `ask` instead for\nowner-facing breed/disease/carrier questions; use THIS for human-disease -> dog-model cross-species queries.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "narrate": {
            "default": false,
            "type": "boolean"
          },
          "question": {
            "type": "string"
          }
        },
        "required": [
          "question"
        ],
        "type": "object"
      },
      "name": "ask_the_graph",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "THE headline query. Given a CanFam4 position (e.g. '5:56189113'), return the variant's global +\npopmax frequency, breed-stratified cross-breed frequencies, ESM2/Pangolin/phyloP pathogenicity, gene\ncontext, linked diseases (v1.1), provenance, and deep links — in one call. Pass breed_context to also\nget that breed's AF + rank. cross_breed_full=True returns all 188 breeds (default: top_n).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed_context": {
            "default": "",
            "type": "string"
          },
          "cross_breed_full": {
            "default": false,
            "type": "boolean"
          },
          "position": {
            "type": "string"
          },
          "top_n": {
            "default": 5,
            "type": "integer"
          }
        },
        "required": [
          "position"
        ],
        "type": "object"
      },
      "name": "ask_variant_context",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Genetic distance between two breeds (top-10-PC Euclidean). Lower = more genetically similar.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed_a": {
            "type": "string"
          },
          "breed_b": {
            "type": "string"
          }
        },
        "required": [
          "breed_a",
          "breed_b"
        ],
        "type": "object"
      },
      "name": "breed_similarity",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Breed profile: top damaging common variants (ESM2<=-5 & breed AF>=5%), n_dogs, breed group.\nDescriptive only — not a health ranking.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed": {
            "type": "string"
          }
        },
        "required": [
          "breed"
        ],
        "type": "object"
      },
      "name": "breed_summary",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Breed-stratified allele frequency. Give a breed (e.g. 'bernese_mountain_dog') plus either a\nvariant position or a gene symbol. Returns AF (+ rank) for the variant, or per-variant AFs in the gene.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed": {
            "type": "string"
          },
          "gene": {
            "default": "",
            "type": "string"
          },
          "variant": {
            "default": "",
            "type": "string"
          }
        },
        "required": [
          "breed"
        ],
        "type": "object"
      },
      "name": "breed_variant_frequency",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "List all 188 breeds with breed-stratified frequencies in the atlas.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "breeds_in_atlas",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "The fused OMIA disease layer as cited atoms. Give a `disease` (name or 'OMIA:001870-9615') for its\ngenes, inheritance, human homolog (OMIM/Mondo bridge), and variant pathogenicity grade (AVCG, ACMG/AMP\n5-tier, curated in OMIA) when graded. Or give a `breed` (e.g. 'doberman_pinscher') for the inherited\nconditions documented in that breed with carrier frequency + confidence tier + grade. Every atom carries\nits source + atom_id. Educational, not diagnostic.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed": {
            "default": "",
            "type": "string"
          },
          "disease": {
            "default": "",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "disease_bridge",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "A canine inherited disease (name or OMIA id) -> its governed OMIA clinical record: mode of inheritance,\ncausal gene(s), curated description (summary / clinical features / molecular genetics / pathology /\nprevalence), clinical signs as HP/MP phenotype terms (-> Monarch), the human OMIM analog + Mondo id, and\nthe evidence base (peer-reviewed reference count + landmark study) -- plus molecular links (variants/breeds)\nwhen the KG carries them. Sourced to OMIA (CC-BY); returns a canonical sniff.world URL. Dog-only.\nEducational, not diagnostic. For fuzzy candidates use search_diseases.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "disease": {
            "default": "",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "disease_links",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Look up a canine inherited disease by name or OMIA id -> its governed OMIA clinical record (inheritance,\ncausal gene(s), curated description, clinical signs, human OMIM analog + Mondo id, evidence base). Sourced\nto OMIA (CC-BY); returns a canonical sniff.world URL. Dog-only. For candidate disambiguation use\nsearch_diseases; for a disease's molecular links use disease_links.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "query": {
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "disease_lookup",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Variants in a gene (by gene symbol), ranked by impact then ESM2 damage. Paginated (limit, default 25);\nreturns total_variants. Use af_min to filter by global AF.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "af_min": {
            "default": 0,
            "type": "number"
          },
          "gene_symbol": {
            "type": "string"
          },
          "limit": {
            "default": 25,
            "type": "integer"
          }
        },
        "required": [
          "gene_symbol"
        ],
        "type": "object"
      },
      "name": "gene_summary",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Top genes by number of variants in the atlas (discovery aid).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "default": 50,
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "genes_indexed",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Atlas metadata: release, DOI, assembly, variant/breed counts, scope banner, and the RPC catalog.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "metadata",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Genetically nearest breeds to the given breed (top-10-PC Euclidean in canine genetic space).\nAnswers 'what breeds are most genetically similar to X?' via the PCA-256 breed co-embedding.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "breed": {
            "type": "string"
          },
          "k": {
            "default": 10,
            "type": "integer"
          }
        },
        "required": [
          "breed"
        ],
        "type": "object"
      },
      "name": "nearest_breeds",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Search the canine disease catalogue by free text -> ranked candidates [{omia_id, disease, url, score}].\nUse before disease_lookup when the exact name is unknown. Dog-only.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "default": 10,
            "type": "integer"
          },
          "query": {
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_diseases",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Faceted hybrid + semantic-ranker search over the whole knowledge base (diseases, breeds, Scout\ndiscoveries). Use for fuzzy/thematic intent ('drug sensitivity in herding dogs', 'breeds prone to eye\ndisease', 'genetically diverse breeds'). entity_type filters to 'disease'|'breed'|'discovery'. filters\nis an OData facet expression for cross-dimension queries, e.g. \"breed_group eq 'herding' and cohort_n ge 30\"\nor \"diversity_tier eq 'severe_bottleneck'\" (facets: type, breed, breed_group, gene, evidence_tier,\nconfidence_tier, diversity_tier, cohort_n). Returns ranked entities with snippets, dimension fields, links.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "entity_type": {
            "default": "",
            "type": "string"
          },
          "filters": {
            "default": "",
            "type": "string"
          },
          "query": {
            "type": "string"
          },
          "top_k": {
            "default": 8,
            "type": "integer"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "semantic_search",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Single-variant lookup by CanFam4 position: ref/alt, global + popmax AF, consequence, gene,\nESM2/Pangolin/phyloP, deleteriousness tier, canonical URL, provenance.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "position": {
            "type": "string"
          }
        },
        "required": [
          "position"
        ],
        "type": "object"
      },
      "name": "variant_lookup",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Filtered discovery over all 9.67M variants. Predicates (combine freely): esm_max (ESM2 LLR <=),\nphylop_min (phyloP >=), popmax_min (popmax AF >=), gene_in (list of gene symbols), consequence,\nimpact (HIGH/MODERATE/LOW/MODIFIER). Returns total_count + a capped list (max 200). Note: popmax may\nbe in a wild population (dingo/village) — check popmax_breed.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "consequence": {
            "default": "",
            "type": "string"
          },
          "esm_max": {
            "default": null,
            "type": "number"
          },
          "gene_in": {
            "default": null,
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "impact": {
            "default": "",
            "type": "string"
          },
          "limit": {
            "default": 50,
            "type": "integer"
          },
          "phylop_min": {
            "default": null,
            "type": "number"
          },
          "popmax_min": {
            "default": null,
            "type": "number"
          }
        },
        "type": "object"
      },
      "name": "variant_search",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:4746f09c93d3b1b3863ac5ac02f0199c05faace0dfd50313fba165d064adf2cb | sha256sum