Doconda
OfficialDoconda's MCP server lets AI agents create, convert, edit, inspect, and retrieve Word, PowerPoint, Excel, PDF, and artifact documents.
Create finished documents (
docx,pdf,pptx,xlsx, or web-page artifacts) from prompts or Markdown, with format, style, quality, retention, and source-file controls.Upload files by local path, public URL, or base64 content, including documents, spreadsheets, PDFs, and images.
Convert uploaded or Doconda-made files between supported formats, with OCR for scanned PDFs and pictures.
Edit existing Word, PowerPoint, Excel, or PDF files using natural-language instructions.
List recent project documents and retrieve document status plus fresh download links.
Get edit reports showing each change with before and after text.
Read data saved in artifact pages, such as poll votes or checklist records.
The remote Doconda MCP server can be attached directly as a tool in the OpenAI Responses API (server_url + bearer API key, with approval settings), so a model can create, review and edit Word, PowerPoint, Excel and PDF documents, or build interactive web-page artifacts, and get back download links and change reports.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
@doconda/mcp
MCP server for Doconda: give your AI agent tools to convert, create and edit Word, PowerPoint, Excel and PDF documents. Editable files, reviewed before delivery, with a PDF and a preview of each page.
Remote server (for your app's agent)
No install: https://api.eu.doconda.com/mcp (Streamable HTTP). Clients with MCP authorization (Claude connectors,
Claude Code, Cursor, MCP Inspector) only need the URL: they open Doconda in the browser to sign in and approve access
to one project, read-only if you prefer. Agent frameworks and model APIs send an API key instead, as
Authorization: Bearer ak_eu_…. With the OpenAI Responses API:
from openai import OpenAI
response = OpenAI().responses.create(
model="gpt-5",
input="Make an Excel with the event budget",
tools=[{
"type": "mcp",
"server_label": "doconda",
"server_url": "https://api.eu.doconda.com/mcp",
"headers": {"Authorization": "Bearer ak_eu_…"},
"require_approval": "never",
}],
)
print(response.output_text)Messages (errors, report texts) come in English; the remote server follows Accept-Language, so send
Accept-Language: es for Spanish.
Not using MCP? The SDKs return the same tools for any model with tool calling: @doconda/sdk · doconda.
Related MCP server: Zileo Docs
Local server (stdio)
With Claude Code:
claude mcp add --transport stdio doconda --env DOCONDA_API_KEY=ak_eu_… -- npx -y @doconda/mcpFor other MCP clients, such as Claude Desktop:
{
"mcpServers": {
"doconda": {
"command": "npx",
"args": ["-y", "@doconda/mcp"],
"env": { "DOCONDA_API_KEY": "ak_eu_…" }
}
}
}Tools
create_document, upload_file, convert_file, edit_document, list_documents, get_document, get_report,
read_artifact_data.
Docs: https://docs.doconda.com/agents/mcp · Examples: https://github.com/B-C-Software/doconda-examples · Get an API key: https://doconda.com
Development
Node 22.18 or later:
npm install
npm run build
npm testThe tests need no API key and make no network calls. This repository is published from Doconda's main repository: open issues and pull requests here, and accepted changes are applied upstream and arrive with the next release.
Available Tools
8 toolsconvert_fileConvert fileAInspect
Convert an uploaded file to another format, with no AI. Word, Markdown, text, HTML and .odt → docx, pdf, md, txt, html, odt, rtf; Excel and CSV → xlsx, csv, pdf, md, txt; PowerPoint → pptx, pdf, md, txt; PDF → docx, md, txt; PNG and JPEG → pdf, md. Scanned PDFs and pictures are read with OCR. md, txt, html and csv come back as text (use md to read any file); the rest as a download link valid 5 minutes. The first 1000 conversions each month are free, then 0.01 € each.
Inputs: to (required), file_id (required).
create_documentCreate documentAInspect
Create a finished document: Word, PDF, PowerPoint, Excel or an artifact (a web page with its own shared database, e.g. a poll or a team checklist). Choose only the format: Doconda works out what kind of document it is (contract, letter, report…) from the request. Give prompt to have it written, or markdown with the content already written. Waits until it is ready and returns download links; after about 4 minutes it returns its id and status instead: call get_document later.
Inputs: data, name, style, format, +6 more.
edit_documentEdit documentAInspect
Change an uploaded Word, PowerPoint, Excel or PDF file as asked (e.g. 'blue headings and add a confidentiality clause'). Only what is asked changes; the rest stays identical. Returns the new file (after about 4 minutes, its id and status instead: call get_document later); get_report lists every change, with the text before and after.
Inputs: file_id (required), instructions (required), quality, max_quality.
get_documentGet documentARead-onlyIdempotentInspect
A document's status and fresh download links (they expire after 5 minutes). Also to check on a document create_document or edit_document returned before it finished.
Inputs: document_id (required).
get_reportGet reportARead-onlyIdempotentInspect
What an edit changed (from edit_document): changes lists each passage added, changed or removed, with the text before and after (empty for a created document). For the status and download links use get_document. Until the document finishes it returns report_not_ready; once its retention ends, content_deleted.
Inputs: document_id (required).
list_documentsList documentsARead-onlyIdempotentInspect
The latest documents made in this project (newest first), with their id and name. Use an id as file_id to convert or edit one, or in source_file_ids to create from it.
Inputs: limit.
read_artifact_dataRead artifact dataARead-onlyIdempotentInspect
What people have saved in an artifact's page (e.g. poll votes): its collections, or one collection's records, newest first.
Inputs: document_id (required), collection.
upload_fileUpload fileAInspect
Upload a file (Word, PDF, PowerPoint, Excel — also the old .doc, .ppt and .xls —, .odt, CSV, TXT, Markdown, HTML, or a PNG, JPEG, GIF or WebP picture; up to 20 MB) to convert or edit it, or to use it as a source. Returns its file_id. Give path for a file on this computer.
Inputs: url, path, filename, content_base64.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool maps to a distinct action on a distinct object: create, upload, edit, status/download, convert, change report, list, and artifact data read. The closest pair, get_document and get_report, is clearly separated by descriptions (status/links vs. edit diffs). No meaningful misselection risk.
All eight tools follow a clean verb_noun snake_case pattern (create_document, upload_file, edit_document, get_document, convert_file, get_report, list_documents, read_artifact_data). The convention is uniform throughout.
Eight tools is well-scoped for a document creation, editing, and conversion service. Each tool covers a necessary lifecycle step without redundancy.
Core lifecycle is covered: create, upload, edit, convert, retrieve status/links, inspect changes, and list. Minor gaps remain, notably no delete_document and no way to write/append records to an artifact's collections (only read_artifact_data exists), but agents can mostly work around these.
Maintenance
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Online office suite for AI agents: edit docs, sheets, slides and PDFs in browser or via MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceA universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.1328 npm140MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for indexing, semantic search, and generation of multi-format documents. Exposes 13 tools over JSON-RPC 2.0 so an LLM can search your local PDF, Excel, and Word files, and create or edit Excel and Word documents.AGPL 3.0
- AlicenseAqualityDmaintenanceMCP server for Word document (.docx) creation and manipulation — the production-grade document automation tool for AI agents.946 npmMIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that enables LLM agents to read, understand, and fill DOCX templates while preserving formatting like bold labels and fonts. It exposes tools for document upload, AST inspection, editing, and validation.1MIT