{
  "$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
  "name": "classifier.dev",
  "title": "classifier.dev",
  "version": "1.0.0",
  "description": "Zero-shot text classification: sort up to 1,000 texts into your own labels in one call, with a calibrated confidence per answer. No API key.",
  "websiteUrl": "https://classifier.dev/mcp-setup",
  "repository": {
    "url": "https://github.com/mrmps/classifier-dev",
    "source": "github"
  },
  "icons": [
    {
      "src": "https://classifier.dev/favicon.svg",
      "mimeType": "image/svg+xml"
    }
  ],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://classifier.dev/mcp",
      "supportedProtocolVersions": [
        "2025-11-25",
        "2025-06-18",
        "2025-03-26"
      ]
    }
  ],
  "icon": "https://classifier.dev/favicon.svg",
  "url": "https://classifier.dev/mcp",
  "serverUrl": "https://classifier.dev/mcp",
  "transport": "streamable-http",
  "instructions": "classifier.dev sorts text into labels you name, many texts per call, with a calibrated confidence on every answer. Use classify_texts for one label per text, classify_multi_label when several can apply, count_labels for a histogram over a corpus, and review_uncertain to pull out only the answers worth a human (or your own) look. Reach for it when reading the inputs is the expensive part: forty search results, a thousand log lines, a backlog of tickets. Under about five items you can already see, just decide yourself. Labels are free text; descriptive names classify better. No key is needed. Limits per IP: 3,000 classifications/min on fast, 200/min on smart. Public smart batches must contain at most 200 texts; a 429 says how long to wait. Docs: https://classifier.dev — the docs are also an MCP server at https://classifier.dev/mcp/docs.",
  "capabilities": {
    "tools": true,
    "resources": false,
    "prompts": false
  },
  "tools": [
    {
      "name": "classify_texts",
      "title": "Classify texts into one label each",
      "description": "Sort up to 1,000 texts into exactly one of your own labels each, with confidence per answer. Use this when you have many items to triage, route, filter or bucket and do not want to read them all: search results before opening them, tickets, log lines, changed files, feedback. Do not use it for fewer than about five items you can already see — just decide. For default Jev, confidence is calibrated (answers >= 0.9 are right ~82-92% of the time; < 0.5 about 30-60%); these measurements do not apply to experimental Laya. so act on the sure ones and look at the rest yourself, or pass tier \"smart\" to have the unsure ones re-asked of a reasoning model.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string",
            "pattern": "^https?://",
            "maxLength": 8192,
            "description": "Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries."
          },
          "include": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "markdown",
                "html"
              ]
            },
            "description": "With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output."
          },
          "inputs": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "maxItems": 1000,
            "description": "1 to 1,000 texts to classify. Results come back in the same order."
          },
          "labels": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 2,
            "maxItems": 100,
            "description": "2 to 100 category names. Descriptive names classify better: \"urgent bug\" beats \"p0\". Add a label like \"none of these\" when none-of-the-above is a real outcome."
          },
          "instructions": {
            "type": "string",
            "description": "Optional extra criteria, e.g. \"judge only the service, ignore the food\"."
          },
          "tier": {
            "type": "string",
            "enum": [
              "fast",
              "smart"
            ],
            "description": "fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane."
          },
          "model": {
            "type": "string",
            "enum": [
              "jev",
              "laya",
              "kev",
              "chunklaya"
            ],
            "description": "Jev is default. Default/explicit jev inputs over 32,000 characters use paid Fast-only long context: up to 250,000 original cl100k_base context tokens total, 20 documents, 32 decisions and a 1 MB body. Requires paid workspace balance or active paid subscription, not signup credit. $0.084/M original context tokens counted once across inputs, independent of dimensions. Final Jev uses selected evidence; eligible chunks may be omitted, disclosed in usage.long_context. No evidence returns 422 long_context_no_evidence without charge. Explicit 'chunklaya' retains legacy opt-in (4,000,000 characters/input, 20 inputs, subject to body limit). 'laya' (512-token context) and 'kev' (8K context) remain experimental alternatives."
          },
          "processing": {
            "type": "string",
            "enum": [
              "fast",
              "bulk"
            ],
            "description": "Optional. Implies Laya if model is omitted; has no effect with explicit Jev. With Laya, omit to select fast for one decision or bulk for batches automatically. Explicit fast accepts one decision. Shared capacity limits can return 429."
          }
        },
        "required": [
          "labels"
        ],
        "oneOf": [
          {
            "required": [
              "inputs"
            ],
            "not": {
              "required": [
                "url"
              ]
            }
          },
          {
            "required": [
              "url"
            ],
            "not": {
              "required": [
                "inputs"
              ]
            }
          }
        ],
        "additionalProperties": false
      },
      "outputSchema": {
        "type": "object",
        "properties": {
          "tier": {
            "type": "string"
          },
          "model": {
            "type": "string"
          },
          "results": {
            "type": "array",
            "description": "One per input, in input order.",
            "items": {
              "type": "object",
              "properties": {
                "label": {
                  "type": "string"
                },
                "confidence": {
                  "type": [
                    "number",
                    "null"
                  ],
                  "description": "0-1; calibration measurements cover Jev, not experimental Laya. Null when the provider returns no score or the smart tier replaces the scored answer."
                },
                "scores": {
                  "type": [
                    "object",
                    "null"
                  ],
                  "additionalProperties": {
                    "type": "number"
                  },
                  "description": "Model preference per supplied label; sums to 1. Does not validate the input or guarantee correctness."
                },
                "escalated": {
                  "type": "boolean",
                  "description": "Smart tier only: this answer was re-asked of the reasoning model."
                }
              },
              "required": [
                "label"
              ]
            }
          },
          "usage": {
            "type": "object",
            "properties": {
              "classifications": {
                "type": "integer"
              },
              "escalated": {
                "type": "integer"
              },
              "ms": {
                "type": "integer"
              }
            }
          }
        },
        "required": [
          "results"
        ]
      },
      "annotations": {
        "title": "Classify texts into one label each",
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": false,
        "openWorldHint": true
      },
      "securitySchemes": [
        {
          "type": "noauth"
        }
      ]
    },
    {
      "name": "classify_dimensions",
      "title": "Classify several dimensions per text",
      "description": "Classify each text by several named dimensions, such as team, urgency and kind, in one request. Returns a label, confidence, scores and model for each field. At most 1,000 item × dimension decisions; every field counts toward the quota. Use per-dimension instructions to define ambiguous categories.",
      "inputSchema": {
        "type": "object",
        "required": [
          "dimensions"
        ],
        "oneOf": [
          {
            "required": [
              "items"
            ],
            "not": {
              "required": [
                "url"
              ]
            }
          },
          {
            "required": [
              "url"
            ],
            "not": {
              "required": [
                "items"
              ]
            }
          }
        ],
        "additionalProperties": false,
        "properties": {
          "url": {
            "type": "string",
            "pattern": "^https?://",
            "maxLength": 8192,
            "description": "Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries."
          },
          "include": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "markdown",
                "html"
              ]
            },
            "description": "With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output."
          },
          "items": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "maxItems": 1000,
            "description": "1 to 1,000 texts to classify. Results come back in the same order."
          },
          "dimensions": {
            "type": "object",
            "minProperties": 1,
            "maxProperties": 20,
            "propertyNames": {
              "minLength": 1,
              "maxLength": 64,
              "pattern": "\\S"
            },
            "description": "Named dimensions. Each is a label array or {labels, instructions}. At most 1,000 item × dimension decisions; definitions at most 16,000 characters combined.",
            "additionalProperties": {
              "oneOf": [
                {
                  "type": "array",
                  "minItems": 2,
                  "maxItems": 100,
                  "uniqueItems": true,
                  "items": {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 200,
                    "pattern": "\\S"
                  }
                },
                {
                  "type": "object",
                  "required": [
                    "labels"
                  ],
                  "additionalProperties": false,
                  "properties": {
                    "labels": {
                      "type": "array",
                      "minItems": 2,
                      "maxItems": 100,
                      "uniqueItems": true,
                      "items": {
                        "type": "string",
                        "minLength": 1,
                        "maxLength": 200,
                        "pattern": "\\S"
                      }
                    },
                    "instructions": {
                      "type": "string",
                      "maxLength": 4000
                    }
                  }
                }
              ]
            }
          },
          "instructions": {
            "type": "string",
            "description": "Optional extra criteria, e.g. \"judge only the service, ignore the food\".",
            "maxLength": 4000
          },
          "tier": {
            "type": "string",
            "enum": [
              "fast",
              "smart"
            ],
            "description": "fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane."
          },
          "model": {
            "type": "string",
            "enum": [
              "jev",
              "laya",
              "kev",
              "chunklaya"
            ]
          },
          "processing": {
            "type": "string",
            "enum": [
              "fast",
              "bulk"
            ],
            "description": "Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit for automatic fast/bulk selection based on item × dimension decisions."
          }
        }
      },
      "annotations": {
        "title": "Classify several dimensions per text",
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": false,
        "openWorldHint": true
      },
      "securitySchemes": [
        {
          "type": "noauth"
        }
      ]
    },
    {
      "name": "classify_multi_label",
      "title": "Tag texts with every label that applies",
      "description": "Like classify_texts, but each text gets every label that applies (possibly none), with an independent 0-1 score per label. Use this for tagging — topics of an article, components touched by a ticket — where one answer is not enough. Set max_labels to cap how many come back per text. Labels scoring >= 0.7 are kept.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "url": {
            "type": "string",
            "pattern": "^https?://",
            "maxLength": 8192,
            "description": "Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries."
          },
          "include": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "markdown",
                "html"
              ]
            },
            "description": "With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output."
          },
          "inputs": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "maxItems": 1000,
            "description": "1 to 1,000 texts to classify. Results come back in the same order."
          },
          "labels": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 2,
            "maxItems": 100,
            "description": "2 to 100 category names. Descriptive names classify better: \"urgent bug\" beats \"p0\". Add a label like \"none of these\" when none-of-the-above is a real outcome."
          },
          "instructions": {
            "type": "string",
            "description": "Optional extra criteria, e.g. \"judge only the service, ignore the food\"."
          },
          "max_labels": {
            "type": "integer",
            "minimum": 1,
            "maximum": 100,
            "description": "At most this many labels per text, most likely first."
          },
          "model": {
            "type": "string",
            "enum": [
              "jev",
              "laya",
              "kev",
              "chunklaya"
            ]
          },
          "processing": {
            "type": "string",
            "enum": [
              "fast",
              "bulk"
            ],
            "description": "Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically."
          }
        },
        "required": [
          "labels"
        ],
        "oneOf": [
          {
            "required": [
              "inputs"
            ],
            "not": {
              "required": [
                "url"
              ]
            }
          },
          {
            "required": [
              "url"
            ],
            "not": {
              "required": [
                "inputs"
              ]
            }
          }
        ],
        "additionalProperties": false
      },
      "outputSchema": {
        "type": "object",
        "properties": {
          "results": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "labels": {
                  "type": "array",
                  "items": {
                    "type": "string"
                  },
                  "description": "Every label scoring >= 0.7, most likely first. May be empty."
                },
                "scores": {
                  "type": [
                    "object",
                    "null"
                  ],
                  "additionalProperties": {
                    "type": "number"
                  },
                  "description": "Independent model preference per supplied label. Does not validate the input or guarantee correctness."
                }
              },
              "required": [
                "labels"
              ]
            }
          },
          "usage": {
            "type": "object",
            "properties": {
              "classifications": {
                "type": "integer"
              },
              "ms": {
                "type": "integer"
              }
            }
          }
        },
        "required": [
          "results"
        ]
      },
      "annotations": {
        "title": "Tag texts with every label that applies",
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": false,
        "openWorldHint": true
      },
      "securitySchemes": [
        {
          "type": "noauth"
        }
      ]
    },
    {
      "name": "count_labels",
      "title": "Count how many texts fall under each label",
      "description": "Classify up to 1,000 texts and return only a histogram: how many landed on each label, and how many the model was unsure about. Use this when you want the shape of a corpus — what share of feedback is bugs vs praise, how many search results are relevant — without pulling a thousand individual answers into context. Use classify_texts when you need the answer per item.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "inputs": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "maxItems": 1000,
            "description": "1 to 1,000 texts to classify. Results come back in the same order."
          },
          "labels": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 2,
            "maxItems": 100,
            "description": "2 to 100 category names. Descriptive names classify better: \"urgent bug\" beats \"p0\". Add a label like \"none of these\" when none-of-the-above is a real outcome."
          },
          "instructions": {
            "type": "string",
            "description": "Optional extra criteria, e.g. \"judge only the service, ignore the food\"."
          },
          "unsure_below": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "default": 0.7,
            "description": "Answers with confidence under this count as unsure."
          }
        },
        "required": [
          "inputs",
          "labels"
        ],
        "additionalProperties": false
      },
      "outputSchema": {
        "type": "object",
        "properties": {
          "total": {
            "type": "integer"
          },
          "counts": {
            "type": "object",
            "additionalProperties": {
              "type": "integer"
            },
            "description": "Label -> how many texts, every label present."
          },
          "unsure": {
            "type": "integer",
            "description": "How many answers fell under unsure_below."
          },
          "unsure_below": {
            "type": "number"
          }
        },
        "required": [
          "total",
          "counts",
          "unsure"
        ]
      },
      "annotations": {
        "title": "Count how many texts fall under each label",
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": false
      },
      "securitySchemes": [
        {
          "type": "noauth"
        }
      ]
    },
    {
      "name": "review_uncertain",
      "title": "Find the texts the classifier was unsure about",
      "description": "Classify up to 1,000 texts and return only the ones whose confidence fell under a threshold (default 0.7), each with its two most likely labels. Use this after a bulk classification to decide which items deserve your own attention: the confident answers can be trusted, these are the ones to read. Returns the index of each item so you can map back to your list.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "inputs": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 1,
            "maxItems": 1000,
            "description": "1 to 1,000 texts to classify. Results come back in the same order."
          },
          "labels": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "minItems": 2,
            "maxItems": 100,
            "description": "2 to 100 category names. Descriptive names classify better: \"urgent bug\" beats \"p0\". Add a label like \"none of these\" when none-of-the-above is a real outcome."
          },
          "instructions": {
            "type": "string",
            "description": "Optional extra criteria, e.g. \"judge only the service, ignore the food\"."
          },
          "below": {
            "type": "number",
            "minimum": 0,
            "maximum": 1,
            "default": 0.7,
            "description": "Return items with confidence under this."
          }
        },
        "required": [
          "inputs",
          "labels"
        ],
        "additionalProperties": false
      },
      "outputSchema": {
        "type": "object",
        "properties": {
          "total": {
            "type": "integer"
          },
          "below": {
            "type": "number"
          },
          "uncertain": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "index": {
                  "type": "integer",
                  "description": "Position in the inputs you sent."
                },
                "text": {
                  "type": "string"
                },
                "label": {
                  "type": "string",
                  "description": "The model's best guess."
                },
                "confidence": {
                  "type": [
                    "number",
                    "null"
                  ]
                },
                "runner_up": {
                  "type": [
                    "string",
                    "null"
                  ],
                  "description": "The second most likely label."
                }
              },
              "required": [
                "index",
                "text",
                "label"
              ]
            }
          }
        },
        "required": [
          "total",
          "uncertain"
        ]
      },
      "annotations": {
        "title": "Find the texts the classifier was unsure about",
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": false
      },
      "securitySchemes": [
        {
          "type": "noauth"
        }
      ]
    }
  ],
  "documentation": "https://classifier.dev/mcp-setup",
  "kind": "product",
  "authentication": {
    "type": "none",
    "description": "Free classification needs no key. Optional Pro bearer keys give 10x rate limits per billing account; partner keys remain supported. RateLimit headers and 429s with Retry-After describe quotas."
  },
  "openapi": "https://classifier.dev/openapi.json",
  "relatedServers": [
    {
      "name": "classifier.dev docs",
      "kind": "docs",
      "description": "The classifier.dev documentation as tools: list, read and search the API reference, benchmark, agent skill, CLI, pricing, privacy, terms and MCP setup guide.",
      "url": "https://classifier.dev/mcp/docs",
      "serverUrl": "https://classifier.dev/mcp/docs",
      "card": "https://classifier.dev/mcp/docs/server-card",
      "transport": "streamable-http",
      "authentication": {
        "type": "none"
      },
      "tools": [
        "list_docs",
        "read_doc",
        "search_docs",
        "get_examples"
      ]
    }
  ]
}