emboss
Emboss operates ONE remote MCP server at https://api.getemboss.ai/mcp (Streamable HTTP). It is OAuth 2.1 protected: an anonymous POST tools/list and an anonymous initialize both returned 401 with WWW-Authenticate: Bearer error="invalid_token", resource_metadata="https://api.getemboss.ai/.well-known/oauth-protected-resource/mcp". The server is listed in the MCP registry as io.github.edwinorange/emboss (record mirrored at /.well-known/mcp.json on both hosts) and packaged for Claude Code (plugin marketplace GetEmboss-ai/emboss-claude-plugin), Claude.ai/Desktop (custom connector), Gemini CLI/Antigravity (GetEmboss-ai/emboss-gemini-extension), ChatGPT and Grok. Emboss ships NO stdio package: every install path is a client configuration pointing at the hosted endpoint.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
list_forms— Forms already in the user's Emboss library.get_form— Status of one form; when ready, its field inventory, download_url and artifact_id.get_usage— This month's usage, free operations remaining, and the billing page link.find_form— Find a blank US federal form in the Emboss library by name, number or alias.create_form— Upload a PDF and detect its fields.delete_form— Permanently removes a form and its PDFs from the user's library. Only call when the user explicitly asks.fill_form— Fill a ready form with values keyed by field id or label.fill_form_from_context— Fill a form using answers pulled out of documents or notes; returns a job_id to poll with get_job.prepare_form— Propose a fill without writing anything into the PDF; returns job_id and proposal_id.get_proposal— Read a proposal — every field's state, candidate values with evidence, and open questions.commit_proposal— Write a proposal into the PDF, render it, check it, and return a receipt (optionally a submission package).verify_form— Check a filled PDF against a form's contract. No model call.read_form— Read a filled PDF's values back out, labelled, without storing the file.send_fax— Send a PDF to a fax number (E.164; US, Canada, Mexico) and get a job id back at once.get_fax— Delivery status and receipt of a send_fax job.add_attachment— Attach a supporting document (PDF, PNG, JPEG) to a proposal before commit.get_job— Status of a fill_form_from_context, prepare_form, or commit_proposal job.suggest_mapping— Propose which spreadsheet column fills which form field.fill_batch— Fill the form once per spreadsheet row, up to 1000 rows.get_batch— Progress of a fill_batch run.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.