BioCosm

Biotech intelligence for AI agents: drugs, targets, diagnostics, PoS estimates, and writeups.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
92%
Integridad del esquema
87%
Calidad de los nombres
100%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~1,944Tokens (definiciones de herramientas)
~1.1 KBTamaño de respuesta típico
Impacto moderado en la atención (1.52% del contexto de 128k)

Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.

Instalar

Instalación con un clic

Agrega esto a tu archivo `claude_desktop_config.json`:

{
  "mcpServers": {
    "biocosm": {
      "url": "https://biocosm-mcp.fly.dev/mcp"
    }
  }
}

Puntos de conexión remotos

https://biocosm-mcp.fly.dev/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (13)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢search_nodes(query, limit)

Search BioCosm nodes by name, gene symbol, target, therapeutic area, or company. Results are ranked: exact name/brand matches first, then partial name matches, with a node-type prior (canonical drug/diagnostic nodes rank above gene-target nodes, which rank above ChEMBL salt-form duplicates). Nodes matched only via description/company/area rank last. Each result includes a `name` field for disambiguation.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search term (e.g. \"breast cancer\", \"pembrolizumab\", \"Merck\")"
    },
    "limit": {
      "default": 20,
      "type": "integer",
      "description": "Maximum results to return (default 20, max 100)"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_node(node_id)

Get full details for a single BioCosm node: identity and all name aliases, classification, gene targets and mechanism, therapeutic areas, companies, revenue history where available (sparse: ~100 drugs, mostly blockbusters, as annualized quarterly estimates; source links when present), probability-of- success predictions for pipeline drugs (with confidence intervals and contributing factors), structured clinical trial outcomes, external cross-references, and writeup availability. Empty fields mean "not in BioCosm's coverage," NOT zero or absent in reality.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "description": "The node identifier (e.g. \"pembrolizumab\", \"trastuzumab\")"
    }
  },
  "required": [
    "node_id"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_writeup(node_id)

Get the full writeup for a BioCosm node, including all sections, citations, structured data, and validation score.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "description": "The node identifier (e.g. \"pembrolizumab\")"
    }
  },
  "required": [
    "node_id"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢list_by_therapeutic_area(area, limit)

List all nodes in a given therapeutic area.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "area": {
      "type": "string",
      "description": "Therapeutic area to search (e.g. \"breast cancer\", \"non-small cell lung cancer\")"
    },
    "limit": {
      "default": 50,
      "type": "integer",
      "description": "Maximum results (default 50)"
    }
  },
  "required": [
    "area"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_company_portfolio(company_name)

Get a company's full drug/diagnostic portfolio from BioCosm.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "company_name": {
      "type": "string",
      "description": "Company name (e.g. \"Merck\", \"Roche\", \"Illumina\")"
    }
  },
  "required": [
    "company_name"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_stats

Get a high-level overview of the BioCosm database: total nodes, writeups, companies, breakdowns by type/status/domain, validation scores, and recent pipeline runs.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true
}
🟢get_staleness_report(limit)

Get writeup staleness report: overall stats, top stale nodes, data source freshness.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 20,
      "type": "integer",
      "description": "Number of top stale nodes to return (default 20)"
    }
  },
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true
}
🟢get_node_freshness(node_id)

Get freshness details for a single node: writeup age, enrichment hash match, staleness score, validation score.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "description": "The node identifier (e.g. \"pembrolizumab\")"
    }
  },
  "required": [
    "node_id"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢find_by_target(target_gene, limit)

Find all drugs that target a specific gene/protein.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "target_gene": {
      "type": "string",
      "description": "Gene symbol or target name (e.g. \"EGFR\", \"KRAS\", \"PD-1\")"
    },
    "limit": {
      "default": 50,
      "type": "integer",
      "description": "Maximum results (default 50, max 200)"
    }
  },
  "required": [
    "target_gene"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢find_by_phase(phase, node_type, limit)

List drugs/diagnostics at a specific clinical phase.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "phase": {
      "type": "string",
      "description": "One of \"approved\", \"on_market\", \"phase3\", \"phase2\", \"phase1\",\n   \"in_development\", \"cleared\", \"ldt\", \"ruo\""
    },
    "node_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional filter — \"drug\", \"pipeline\", \"diagnostic\", \"target\""
    },
    "limit": {
      "default": 100,
      "type": "integer",
      "description": "Maximum results (default 100, max 500)"
    }
  },
  "required": [
    "phase"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢find_related(node_id, link_type, limit)

Find nodes connected to a given node. Three relationship types are derived on-the-fly: - "drug_target": for a drug, the targets it hits (and vice versa for a target node, the drugs that hit it) - "same_company": drugs sharing a company with this node - "same_target_class": drugs with the same mechanism_class

Esquema de entrada

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "description": "Source node identifier"
    },
    "link_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional filter — one of \"drug_target\", \"same_target_class\",\n       \"same_company\". If None, returns all three groups."
    },
    "limit": {
      "default": 30,
      "type": "integer",
      "description": "Maximum results per link type (default 30)"
    }
  },
  "required": [
    "node_id"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_pos_score(node_id)

Get the Probability of Success estimate for a node, including the base rate, adjustment factors with reasoning, confidence interval, and model version. Returns None for nodes without a PoS score (typically only late-stage pipeline drugs are scored).

Esquema de entrada

{
  "type": "object",
  "properties": {
    "node_id": {
      "type": "string",
      "description": "Node identifier"
    }
  },
  "required": [
    "node_id"
  ],
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_coverage

Report BioCosm's actual data coverage so you never mistake missing data for a real-world zero. An empty or absent field on a node means "not in BioCosm's data," never a true zero. BioCosm is AI-generated and may contain errors.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada13 herramientas
verificadoversión no registrada13 herramientas