Emboss
UnclaimedEmboss turns any PDF form into a fillable one, fills it from data or supporting documents, reads a filled form back, and faxes the result to a US, Canadian or Mexican fax number. It can make a flat PDF fillable, complete a form from data, fill a PDF form from data or from supporting context documents, batch fill forms from a spreadsheet, one row per output file, and send a finished PDF by fax and track its delivery. Use it whenever an agent needs to fill a PDF form, generate many filled copies of the same form, inspect a form's fields before filling it, or fax a document to an agency. Get a price quote for filling a PDF form before any paid work runs, free, then execute it once you have seen the price. Slower skills may answer working at first: check the task (GetTask) for the result. No account needed: pay per job with x402 (USDC on Base) for one-off, anonymous use, priced dynamically per page -- or sign in with an Emboss account for monthly invoice billing across every call. A pay-per-call API is also available at https://api.getemboss.ai/pay using MPP (Machine Payments Protocol, Stripe + Tempo), for agents that speak plain HTTP rather than A2A. Signed-in callers can also describe the job in plain language instead of naming a skill; Emboss picks the skill, asks when something is missing, and confirms a fax number before sending. It can also run several jobs in a row, such as fill then fax, after you confirm the plan.
- Contact address
- https://api.getemboss.ai/a2a
- Agent card
- https://api.getemboss.ai/.well-known/agent-card.json
- Protocol
- A2A 0.3 · card version 1.0.0
- Provider, per the card
- Emboss · https://getemboss.ai
- Documentation, per the card
- https://getemboss.ai/docs/a2a
Skills, as the card declares them
Repeated from the card. Not checked by us.
Make a PDF fillable
Turn a flat or scanned PDF form into a fillable PDF with detected fields. Make a flat PDF fillable. Input: a flat (non-fillable) PDF file, or a `library` slug from find_form to start from a blank government form Emboss already keeps. Output: a form_id and the fields detected on the PDF (each field's id, label, kind, whether it is required, its options, group and description), ready for fill_form or fill_from_context. Adobe LiveCycle XFA forms are filled through their datasets, and a fill from documents also returns the values as a data export; a dynamic XFA form whose layout flows or repeats rows is accepted with no fields to fill (warning xfa_dynamic_form). Also: detect form fields in a PDF; add fillable fields to a document; extract a PDF form schema; make a government or business form fillable; XFA forms; Adobe LiveCycle forms; Adobe dynamic forms. Optional input: retention (ephemeral or account_default; the account's own setting by default), which applies only when the call create…
tags: document-processing, form-schema, forms, make-fillable, pdf, pdf-form-fields, xfa
Fill a form from data
Fill a PDF form from structured data such as JSON or key-value answers. Fill a PDF form from data. Input: a form_id (from make_fillable or find_forms) or a flat PDF file, plus a values object mapping field names to answers. Output: a filled PDF file, the form_id, and any values that matched no field. Also: fill a PDF form from JSON; populate form fields from data; complete a PDF application from known values; write answers into a form. Optional input: retention (ephemeral or account_default; the account's own setting by default), which applies only when the call creates the form; an existing form keeps its own setting. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Add "dry_run": true to the data part to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
tags: data-entry, fill-pdf, form-filling, forms, json, pdf
Fill a form from context documents
Fill a PDF form using facts found in supporting documents. Complete a form from data found in supporting documents. Input: a form_id, a PDF file, or a `library` slug from find_form, plus one or more context files and/or freeform context text (a resume, a prior filing, notes) to extract answers from. Output: a filled PDF file, the form_id, how many fields were filled and dropped, and any warnings. Also: fill a PDF form from DOCX, spreadsheets, images, JSON, or other documents; pre-fill a government form from supporting paperwork; complete an application from a resume or company details; extract answers from context documents into a form. Optional input: retention (ephemeral or account_default; the account's own setting by default), which applies only when the call creates the form; an existing form keeps its own setting. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Add "dry_run": true to the data part to rehearse this…
tags: context-fill, document-extraction, document-processing, extraction, fill-pdf, form-filling, forms, pdf
Prepare a form from documents
Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Prepare a form instead of filling it. Input: a form_id, a PDF file, or a `library` slug from find_form, plus one or more context files and/or freeform context text, and an optional policy (safe or strict). Output: a proposal_id and the proposal itself, listing every field's proposed answer with the document it came from, the questions still open, and the signatures and attachments a person still has to supply. Nothing is written into the PDF until a later call commits it. Also: review a form before it is filled; see which answers came from which document; find the gaps in an application; check a form for conflicting information; propose answers for review instead of writing them. Optional input: retention (ephemeral or account_default; the account's own setting by default), which applies only when the call creates the…
tags: agents, extraction, forms, pdf, review
Batch fill forms from a spreadsheet
Fill one copy of a PDF form for every row of a spreadsheet. Batch fill forms from a spreadsheet. Input: a form_id (required), plus a CSV file part or csv_text with one row per filled copy, and an optional column-to-field mapping. Output: one filled PDF per row and the form_id. Also: batch fill PDF forms from a CSV or Excel file; mail-merge a PDF form; generate many filled forms from a table of records. Optional input: retention (ephemeral or account_default) is accepted but changes nothing: a batch fills an existing form, which keeps its own setting. Add "dry_run": true to the data part to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
tags: batch, fill-pdf, forms, mail-merge, pdf, spreadsheet
Read a batch fill's rows, a page at a time
Read the rows of a batch fill, a page at a time. Free. Input: the batch_id from fill_batch, plus an optional limit (1 to 100, default 100) and offset (default 0). Output: the batch's status and counts, up to limit rows (each with its download link or error), the zip link once the batch is done, and next_offset, where the next page starts (empty on the last page, and while the batch is still running). Works for the account that ran the batch.
tags: pdf, forms, batch, spreadsheet
Suggest a column-to-field mapping
Propose which spreadsheet columns fill which PDF form fields. Suggest how spreadsheet columns map to form fields before a batch fill. Input: a form_id (required), plus a CSV file part, csv_text, or a list of column names (columns). Output: a suggested mapping from columns to field names for review. Also: map CSV columns to form fields; match spreadsheet headers to a PDF form; plan a batch fill. Add "dry_run": true to the data part to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
tags: form-schema, forms, mapping, pdf, spreadsheet
Find previously processed forms
Find forms previously made fillable, by title search and state. Input: an optional query string, state filter (ready, processing, failed, or all), and a result limit and offset. Output: a list of matching forms, each with its id, title, state, page count and field count, and next_offset, where the next page starts (empty on the last page).
tags: pdf, forms, search
Find a blank government form
Find a blank government form in the Emboss library by name or number, ready to fill. Find a blank government form in the Emboss library, by name, number, alias or place. Input: a query string such as 'W-9', '1099-NEC' or 'taxpayer identification', and optionally country, region (a state code such as 'CA') or category. Or leave the query empty and give region, country or category to list every form that fits. Output: each matching form's slug, title, agency, number, place, edition and page count, a note when the library holds a different year or needs to know the state, and next_offset when more matches follow (an optional limit and offset page through them). Pass a slug as `library` on make_fillable or fill_from_context to start from that form instead of uploading one. Also: look up a blank IRS tax form; find a W-9, a 1099-NEC or an I-9 to fill in; get a blank government form by its number; search a library of government forms by name, number or place.
tags: form-schema, forms, government-forms, library, pdf, search
Get a form's status and field inventory
Get a form's current status and field inventory. Input: a form_id. Output: the form's state (ready, processing, or failed), title, page count, and field list.
tags: pdf, forms, inspection
Commit a proposal
Write or confirm the answers, render the form with text that fits, check it, and return the PDF with a report and a receipt, or one submission package. Commit a proposal from prepare: write any remaining values, render the PDF with text that fits, check it, and return the filled PDF with a report and a receipt. Input: a proposal_id from prepare, plus any values still needed (field_id, value, and an optional note), a confirm list of field ids whose proposed value is accepted as-is, an optional policy (safe or strict), and an optional package flag. With package the output is one submission package as well: the filled form, the proposal's attachments in the order the form asks for them, and the receipt embedded in the file. Output: a job_id; when the task completes, the verification result, a receipt link, the filled PDF, and the package when one was asked for. Checkboxes take yes or no; yes ticks that box. In a Yes/No pair, say yes to the box you want; two yeses in one pair are refused.…
tags: agents, forms, pdf
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 15 Nov 2026, 13:06 UTC
- The contact address the card names answered (405) — 15 Nov 2026, 13:06 UTC
- Both URLs passed our egress policy — 15 Nov 2026, 13:06 UTC
First recorded by Agent Galaxy 24 Oct 2026, 00:05 UTC— the day this card's address entered our records.