Smart Data Extractor

Working · 74 ms

io.github.lazymac2x/smart-data-extractorv1.0.0

smart-data-extractor MCP server on Cloudflare Workers · REST + MCP JSON-RPC · free tier

Web Search Data & Databases

Source Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://api.lazy-mac.com/smart-data-extractor/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

auto_schema_learn

Idempotent · 30s timeout · Automatically infer JSON Schema from sample data without extraction. Pass `idempotency_key` to deduplicate within 5 minutes.

sample_datastring, required

Representative sample data as JSON string (array of objects or single object). Schema is inferred from structure; use first 1-10 rows for array samples. Max 200KB.

idempotency_keystring

Optional cache key (UUID/string) for 5-minute deduplication. Repeat calls with same key return cached inferred schema instantly.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (4)

auto_schema_learn

Idempotent · 30s timeout · Automatically infer JSON Schema from sample data without extraction. Pass `idempotency_key` to deduplicate within 5 minutes.

Argument	Type	Description
sample_data*	string	Representative sample data as JSON string (array of objects or single object). Schema is inferred from structure; use first 1-10 rows for array samples. Max 200KB.
idempotency_key	string	Optional cache key (UUID/string) for 5-minute deduplication. Repeat calls with same key return cached inferred schema instantly.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "sample_data"
  ],
  "properties": {
    "sample_data": {
      "type": "string",
      "examples": [
        "{\"product_id\":123,\"title\":\"Laptop Pro\",\"price\":1299.99,\"in_stock\":true}",
        "[{\"id\":1,\"email\":\"[email protected]\",\"verified\":true},{\"id\":2,\"email\":\"[email protected]\",\"verified\":false}]",
        "{\"name\":\"Report Q1\",\"sections\":[{\"title\":\"Sales\",\"value\":50000}]}"
      ],
      "description": "Representative sample data as JSON string (array of objects or single object). Schema is inferred from structure; use first 1-10 rows for array samples. Max 200KB."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional cache key (UUID/string) for 5-minute deduplication. Repeat calls with same key return cached inferred schema instantly."
    }
  },
  "additionalProperties": false
}

batch_extract

Idempotent · 30s timeout · Extract data from multiple sources (JSON/JSONL/text) with a single consistent schema. Pass `idempotency_key` to deduplicate within 5 minutes.

Argument	Type	Description
schema	object	Optional target JSON Schema (draft-07) applied to all sources. If omitted, inferred from first source and reused across remaining sources. Enables consistent field extraction from diverse formats.
sources*	array	Array of 1-100 data sources to extract from. Each source includes type (format) and content (raw data).
idempotency_key	string	Optional deduplication key (UUID/string) for 5-minute cache. Identical batch calls (same sources + schema + key) return cached results instantly.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "sources"
  ],
  "properties": {
    "schema": {
      "type": "object",
      "description": "Optional target JSON Schema (draft-07) applied to all sources. If omitted, inferred from first source and reused across remaining sources. Enables consistent field extraction from diverse formats."
    },
    "sources": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "type",
          "content"
        ],
        "properties": {
          "type": {
            "enum": [
              "json",
              "jsonl",
              "text"
            ],
            "type": "string",
            "description": "Source format: \"json\" (single object or array), \"jsonl\" (newline-delimited JSON objects), \"text\" (key:value pairs delimited by commas/semicolons)"
          },
          "content": {
            "type": "string",
            "description": "Raw source content (max 200KB per source). For jsonl: each line must be valid JSON. For text: format \"key1:value1,key2:value2\"."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 100,
      "minItems": 1,
      "description": "Array of 1-100 data sources to extract from. Each source includes type (format) and content (raw data)."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional deduplication key (UUID/string) for 5-minute cache. Identical batch calls (same sources + schema + key) return cached results instantly."
    }
  },
  "additionalProperties": false
}

extract_from_api

Idempotent · 30s timeout · Extract structured data from API response JSON with schema adaptation. Pass `idempotency_key` to deduplicate within 5 minutes.

Argument	Type	Description
schema	object	Optional target JSON Schema (draft-07) for field extraction. If omitted, inferred from content structure. Enforces consistent field extraction across multiple API responses.
content*	string	API response body as raw JSON string (max 200KB). Can be single object, array of objects, or array of primitives. Automatically parsed and validated.
idempotency_key	string	Optional deduplication key (UUID or unique string) for 5-minute cache. Identical calls return cached result instantly.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "content"
  ],
  "properties": {
    "schema": {
      "type": "object",
      "description": "Optional target JSON Schema (draft-07) for field extraction. If omitted, inferred from content structure. Enforces consistent field extraction across multiple API responses."
    },
    "content": {
      "type": "string",
      "examples": [
        "{\"id\":1,\"name\":\"Alice\",\"role\":\"admin\"}",
        "[{\"id\":1,\"name\":\"Alice\"},{\"id\":2,\"name\":\"Bob\"}]",
        "[{\"user\":{\"id\":1,\"name\":\"Alice\"},\"status\":\"active\"}]"
      ],
      "description": "API response body as raw JSON string (max 200KB). Can be single object, array of objects, or array of primitives. Automatically parsed and validated."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional deduplication key (UUID or unique string) for 5-minute cache. Identical calls return cached result instantly."
    }
  },
  "additionalProperties": false
}

extract_from_url

Idempotent · 30s timeout · Extract structured data from URL content with auto schema learning. Pass `idempotency_key` to deduplicate identical calls within 5 minutes.

Argument	Type	Description
url*	string	HTTP(S) URL to fetch (will auto-download and parse), or raw content string (up to 200KB). Max 200KB after fetch.
schema	object	Optional pre-defined JSON Schema (draft-07). If omitted, schema is auto-inferred from content. Provide to enforce strict field extraction and type coercion.
idempotency_key	string	Optional UUID or unique identifier for 5-minute deduplication cache. Same key + tool = cached result in <5ms, zero re-fetching.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "examples": [
        "https://api.github.com/users/octocat",
        "https://example.com/page.html",
        "{\"name\":\"John Doe\",\"age\":30,\"email\":\"[email protected]\"}"
      ],
      "description": "HTTP(S) URL to fetch (will auto-download and parse), or raw content string (up to 200KB). Max 200KB after fetch."
    },
    "schema": {
      "type": "object",
      "description": "Optional pre-defined JSON Schema (draft-07). If omitted, schema is auto-inferred from content. Provide to enforce strict field extraction and type coercion."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional UUID or unique identifier for 5-minute deduplication cache. Same key + tool = cached result in <5ms, zero re-fetching."
    }
  },
  "additionalProperties": false
}