SafetyDataSheetAPI
Extract safety data sheet (SDS/MSDS) PDFs into a fixed 16-section JSON record.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"sds-extraction": {
"url": "https://safetydatasheetapi.com/mcp"
}
}
}远程端点
https://safetydatasheetapi.com/mcpstreamable-http它能做什么
工具清单
工具（4）
🟢extract_sds(file_url, file_base64, filename, language_hint, schema_version, ...)
Extract one Safety Data Sheet PDF into a normalized 16-section record (product identification, hazards, composition, first aid, transport, regulatory, and more) plus a confidence_score and warnings. Provide the PDF as file_url (a public https URL) or file_base64. Billed per document from prepaid credit (failures are not billed). Requires an API key.
输入模式
{
"type": "object",
"properties": {
"file_url": {
"type": "string",
"format": "uri",
"description": "Public https URL of the SDS PDF."
},
"file_base64": {
"type": "string",
"description": "Base64-encoded SDS PDF bytes (use for small files)."
},
"filename": {
"type": "string",
"description": "Optional file name, for example acetone-sds.pdf."
},
"language_hint": {
"type": "string",
"description": "Optional language hint such as en, de, fr."
},
"schema_version": {
"type": "string",
"description": "Optional output schema version."
},
"include_formats": {
"type": "array",
"items": {
"type": "string",
"enum": [
"xml",
"csv"
]
},
"description": "Also return the XML and/or CSV renderings. Omitted by default to keep results compact."
}
},
"oneOf": [
{
"required": [
"file_url"
]
},
{
"required": [
"file_base64"
]
}
]
}🟡submit_bulk_extraction(file_urls, callback_url, language_hint, schema_version, idempotency_key)
Submit up to 10 SDS PDFs (public https URLs) as one asynchronous job. Returns a job_id; poll get_bulk_job until status is completed or failed. Reuse the same idempotency_key when retrying so no duplicate job is created. Billed per document from prepaid credit, reserved up front and released for any file that fails. Requires an API key.
输入模式
{
"type": "object",
"properties": {
"file_urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"minItems": 1,
"maxItems": 10,
"description": "Public https URLs of SDS PDFs."
},
"callback_url": {
"type": "string",
"format": "uri",
"description": "Optional https URL that receives a signed webhook when the job finishes."
},
"language_hint": {
"type": "string"
},
"schema_version": {
"type": "string"
},
"idempotency_key": {
"type": "string",
"description": "Caller-chosen unique key; a repeat returns the existing job."
}
},
"required": [
"file_urls"
]
}🟢get_bulk_job(job_id)
Get the status and per-file results of a bulk extraction job created by submit_bulk_extraction. Read-only and safe to repeat. Requires an API key.
输入模式
{
"type": "object",
"properties": {
"job_id": {
"type": "string",
"description": "The job_id returned by submit_bulk_extraction."
}
},
"required": [
"job_id"
]
}🟢get_account
Get the prepaid credit balance, price per document, and the last 30 days of usage for the account that owns the API key. Read-only. Requires a per-customer API key.
输入模式
{
"type": "object",
"properties": {}
}社区
证据