safetydatasheetapi
https://safetydatasheetapi.com
Registry code: 886f9f2158808ac2
Extracts Safety Data Sheet (SDS/MSDS) PDFs into normalized 16-section JSON, with a confidence score and warnings. Use extract_sds for one document; use submit_bulk_extraction then get_bulk_job for up to 10 documents. Each document is billed from the account's prepaid credit (see get_account for the balance and price; a failed extraction is not billed, and a 402 insufficient_credit error means credit must be added). Route results with warnings or a low confidence_score to human review before using them for compliance decisions. Documentation: https://safetydatasheetapi.com/api-docs/
- endpoint
- https://safetydatasheetapi.com/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is safetydatasheetapi live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is safetydatasheetapi free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does safetydatasheetapi have?
- 4 tools: get_account, get_bulk_job, extract_sds, submit_bulk_extraction.
- Is safetydatasheetapi safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 4 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_account auth-required 1h ago
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.
{ "type": "object", "properties": {} }arguments 4 linesget_bulk_job auth-required 1h ago
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.
{ "type": "object", "required": [ "job_id" ], "properties": { "job_id": { "type": "string", "description": "The job_id returned by submit_bulk_extraction." } } }arguments 12 linesextract_sds auth-required never probed
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.
{ "type": "object", "oneOf": [ { "required": [ "file_url" ] }, { "required": [ "file_base64" ] } ], "properties": { "file_url": { "type": "string", "format": "uri", "description": "Public https URL of the SDS PDF." }, "filename": { "type": "string", "description": "Optional file name, for example acetone-sds.pdf." }, "file_base64": { "type": "string", "description": "Base64-encoded SDS PDF bytes (use for small files)." }, "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": { "enum": [ "xml", "csv" ], "type": "string" }, "description": "Also return the XML and/or CSV renderings. Omitted by default to keep results compact." } } }arguments 49 linessubmit_bulk_extraction auth-required never probed
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.
{ "type": "object", "required": [ "file_urls" ], "properties": { "file_urls": { "type": "array", "items": { "type": "string", "format": "uri" }, "maxItems": 10, "minItems": 1, "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." } } }arguments 33 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id886f9f2158808ac2.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/886f9f2158808ac2/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/886f9f2158808ac2?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.