Re:portFlow
OfficialOne-line summary: Re:port Flow MCP lets an AI authenticate to Re:port Flow and turn workspace report templates into single or batch PDFs, with sync/async generation and download support.
Authenticate with Re:port Flow via OAuth2, including forced re-authentication.
List available workspace templates and retrieve each design’s parameter schema.
Generate a single PDF synchronously from a template and parameter values.
Generate multiple PDFs in one synchronous batch and receive them as a ZIP.
Start single-PDF generation asynchronously and later download the finished file.
Start batch PDF generation asynchronously and later download the resulting ZIP.
Use
suggest_paramson Sampling-capable clients to turn natural-language briefs into valid template parameters.Return local file paths in stdio/local mode and output-history URLs in remote/HTTP mode.
Save outputs to a requested directory or the client workspace/temp fallback.
Enforce that the AI checks template parameters first and asks users for missing values rather than inventing business data.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Re:port Flow MCP
Official display name: Re:port Flow MCP. Package and implementation identifier: reportflow-mcp. Legacy search aliases: ReportFlow MCP Server and ReportFlow.
Overview
An MCP (Model Context Protocol) server that turns your Re:port Flow templates into PDF reports — invoices, contracts, statements, anything you've designed — straight from Claude or any other MCP-compatible AI agent.
Related MCP server: PDF Tools AI MCP
Features
Generate PDFs from natural-language requests like "create an invoice for Acme Corp totalling $300"
Expose your Re:port Flow designs and their parameter schemas directly to the AI as MCP Resources
Bulk-generate many PDFs and download them as a single ZIP
Save outputs to whichever workspace folder the user is currently in (Claude Desktop / Claude Code / Cursor / VS Code all supported)
Agent Skill
Agents that should follow a procedure (not just read the protocol) use
skills/re-port-flow/SKILL.md. Copy that
directory into Claude Code / Codex .agents/skills or a Cursor project skill
folder. PDF generation always goes to https://mcp.re-port-flow.com/mcp.
The Hugging Face Space MCP (org card)
is gallery-only — add it from the Space MCP badge → Add to MCP tools,
not as a substitute for the product endpoint.
Setup
Re:port Flow MCP runs in two ways — pick whichever matches your client.
Remote server (claude.ai / web clients) — Streamable HTTP
Add Re:port Flow as a custom connector pointing at the hosted endpoint:
https://mcp.re-port-flow.com/mcpIn Claude (claude.ai) go to Settings → Connectors → Add custom connector and paste the URL above. Authentication is handled in-app via OAuth (see Authentication) — nothing to install locally.
Local server (Claude Desktop / Claude Code / Cursor) — stdio via npx
Add the following to your config file (.mcp.json, claude_desktop_config.json, ~/.cursor/mcp.json, etc.):
{
"mcpServers": {
"reportflow": {
"command": "npx",
"args": ["-y", "reportflow-mcp"]
}
}
}That's the whole setup. No env vars, no API keys, no secrets to manage.
VS Code (MCP-enabled builds)
Same JSON in .vscode/mcp.json.
Requirements
Remote: an MCP client that supports custom HTTP connectors (e.g. claude.ai). No local install.
Local (stdio): Node.js 22.23.4 or later in the 22.x line (
engines: ^22.23.4) and a browser available during the first login. Install a patched Node.js separately;npxdownloads the MCP package. The minimum patch requirement includes the 2026-10-21 Node.js security fixes.A Re:port Flow account (either way).
Supported protocol revisions
Both transports (stdio / Streamable HTTP) serve two MCP protocol generations from a single endpoint:
2026-07-28(current) — stateless per-request protocol. Modern clients discover it viaserver/discover; no session header, requests carry their protocol version in_meta.2025-era revisions (
2025-11-25,2025-06-18,2025-03-26,2024-11-05,2024-10-07) — classicinitializehandshake, kept for backwards compatibility with existing clients (Claude Desktop, claude.ai custom connectors, Cursor, ChatGPT, n8n, …).
Version selection is automatic on both transports: modern clients probe with server/discover, legacy clients keep sending initialize — no configuration is required on either side, and existing connections keep working unchanged.
Either handshake also returns MCP instructions: a short brief telling the connected AI what Re:port Flow does and how to reach a first PDF (gallery search → copy → parameters → generate), so it can offer to create a document right after you connect instead of waiting to be asked. How closely a client follows those instructions is up to that client.
A2A (Agent2Agent)
The remote server also speaks A2A v1.0 over the JSON-RPC binding:
Agent Card:
https://mcp.re-port-flow.com/.well-known/agent-card.jsonEndpoint:
POST https://mcp.re-port-flow.com/a2a(SendMessage)
Each A2A skill is one of the MCP tools above (the skill id is the tool name). Send a message with a data part {"skill": "<tool name>", "arguments": {...}}; the arguments follow that tool's input schema, and the call runs through the same authorization and workspace permissions as MCP. Authorize with the same OAuth flow (the MCP access token works as-is). Streaming, push notifications and task retrieval are not supported: every SendMessage returns a finished task.
Authentication
Remote (claude.ai)
When you add the connector, Claude runs the OAuth flow for you: Sign in → pick a workspace → consent. Tokens are held by the client — there's no local keychain or browser step to manage.
Local (stdio)
After reloading the MCP client, ask the AI:
Authenticate with Re:port Flow
A browser window opens. Sign in → pick a workspace → consent, and you're
done. Tokens are stored in your OS keychain (macOS Keychain / Windows
Credential Manager / Linux libsecret), with a chmod-0600 file fallback, and
are refreshed automatically.
Usage examples
Each example below is a prompt you can paste as-is; the AI picks the right tools.
1. Generate a single PDF (list → schema → generate)
Using the invoice template, create a PDF for Acme Corp totalling $330.
The AI lists designs with list_templates, fetches the parameter schema with
get_design_parameters, fills in the values, and calls generate_pdf_sync.
Remote: returns
fileUrl— the output-history page of the Re:port Flow web app (sign-in required). It is not a direct file download link.Synchronous generation times out after 60 seconds (the API returns
504); usegenerate_pdfs_asyncfor anything that may take longer.Local: also saves the file and returns its absolute path.
2. Batch-generate many PDFs
From the statement template, generate one PDF per customer (Acme $100, Globex $250, Initech $80) and give them to me together.
Local (stdio):
generate_pdfs_syncwrites a single ZIP to your workspace.Remote:
generate_pdfs_asyncruns the batch and returns a request id plus the output-history page URL (url).get_generation_statustells you when the batch has finished or failed.
3. Async generate, then download (local)
Kick off the contract PDF in the background, then download it once it's ready.
The AI calls generate_pdf_async (returns a requestId immediately), checks
progress with get_generation_status, then calls download_file to save the
finished PDF. The batch equivalent is generate_pdfs_async → download_zip.
If a download is attempted while the file is still being generated, the tool
reports FILE_NOT_READY with the number of seconds to wait instead of failing.
These download tools are stdio-only; on the remote server the sync/async tools
return the output-history page URL instead.
requestId, fileId and designId are short alphanumeric strings (for
example 0eUDdgAjNXrrItA2), not UUIDs.
Tip — natural-language params: on a Sampling-capable client you can ask "draft the params for a $1,000 invoice to A社" and the AI will call
suggest_paramsto turn the brief into a validparamsobject before generating.
4. Start from zero templates (gallery → copy → generate)
I don't have any templates yet — create an invoice PDF for Acme Corp.
When list_templates is empty, the AI searches the public template gallery
with search_gallery_templates, shows you the candidates, copies your pick
into your workspace with copy_gallery_template, and then proceeds with the
normal flow (get_design_parameters → generate_pdf_sync). The copy always
lands in the workspace you selected on the OAuth consent screen — the AI
cannot target any other workspace.
If the search finds nothing, the result carries a templateSite link to the
template gallery site, where you
can browse the designs. Share the page URL of the one you like
(/templates/{slug}) and the AI copies it by that slug.
Slash commands
Command | Purpose |
| Step-by-step recipe for a single PDF |
| Recipe for batch PDF generation |
| Quick feature tour |
Where files are saved (local mode)
Output location is resolved in this order:
Explicit instruction from the user (e.g. "save to my Desktop")
The currently-open workspace root (Claude Code / Cursor / VS Code)
The OS temp directory as fallback
Build your own agent
The setup above assumes an MCP client that manages its own connection and login. If you are writing the agent yourself — Hugging Face Agents, a custom tool loop, or raw HTTP — the hosted endpoint is open to you directly:
https://mcp.re-port-flow.com/mcpagents.md — the agent-facing guide: transport details, the ten HTTP tools, the OAuth flow, model selection, and the rules an agent has to follow (never invent business data;
copy_gallery_templateis not idempotent;passthroughvalues end up in the PDF's metadata).examples/ — runnable Python, JavaScript and curl clients, plus a script that walks the OAuth flow and prints an access token.
initialize and tools/list work without credentials, so you can discover the
toolset before wiring up authentication. Every tools/call needs a Bearer token.
Hugging Face
Re:port Flow is on the Hub at
huggingface.co/reportflow. The Hugging
Face SDKs have no MCP OAuth flow of their own, so fetch a token once with
examples/oauth/get-token.sh and inject it as
an Authorization header — see
examples/python/hf_mcp_client.py and
examples/javascript/hf-mcp-client.mjs.
Reference
Tools (called by the AI)
Tool | Purpose |
| First-time / re-authentication |
| List available designs |
| Fetch the parameter schema for a design |
| Generate one PDF (sync returns path; async returns request ID) |
| Generate many PDFs (returns a ZIP) |
| Check an async request ( |
| Download artifacts produced by async tools (stdio only). Returns |
| Translate a natural-language brief into a |
| ChatGPT connector convention tools (single string argument), closed-world ( |
| Search the public template gallery (no auth needed) by keyword/category. Returns candidate templates that are not yet in your workspace — their |
| Fetch full details of one public gallery template by |
| Write tool. Copy a gallery template into the workspace you authorized (the target workspace is fixed by your access token and cannot be passed as an argument). Returns |
Resources (attachable as AI context)
URI | Contents |
| List of available designs |
| Parameter schema for one design |
| Catalog of error messages from the Content Service |
| Server feature overview |
Prompts (slash-command recipe cards)
/generate_pdf, /generate_pdfs, /reportflow_help — pass arguments and the AI follows the prepared workflow.
Troubleshooting
Symptom | Fix |
Error containing | Ask the AI: "re-authenticate with Re:port Flow" |
|
|
No keychain available on Linux | Falls back automatically to a chmod-0600 file under |
Browser cannot open over SSH / remote shell | Authenticate once on a local machine; afterwards the cached token works on remote hosts |
Privacy
Re:port Flow MCP is a thin client: it forwards your requests to your own
Re:port Flow account and returns the generated PDFs. It does not sell or share
your data with third parties. Authentication tokens are stored locally (OS
keychain, or a chmod-0600 file fallback) and are sent only to Re:port Flow's
own services — during the OAuth login, and as a Bearer credential on each
authenticated API call (listing templates, generating or downloading PDFs).
They are never shared with any third party.
For the full privacy policy — what is collected, how long it is retained, and how it is handled — see: lp.re-port-flow.com
Security
The hosted endpoint validates the Host header (DNS-rebinding protection) and
rejects structurally invalid Origin headers with 403 Forbidden, per the MCP
Streamable HTTP specification's Security requirements. Authentication is
Bearer-token only — no cookies, and CORS never allows credentials. The full
policy and its threat model are documented in
docs/security.md (Japanese).
Support
Need help, found a bug, or have a directory-review question?
Re:port Flow (privacy & support): https://lp.re-port-flow.com
GitHub Issues: https://github.com/re-port-flow/reportflow-mcp/issues
License
MIT — see LICENSE.
Links
Re:port Flow: https://re-port-flow.com
Privacy & Support: https://lp.re-port-flow.com
Hugging Face: https://huggingface.co/reportflow
Agent guide: agents.md
Examples: examples/
Issues: https://github.com/re-port-flow/reportflow-mcp/issues
Available Tools
10 toolsauthenticateAInspect
ReportFlow への OAuth2 認証を行います。ブラウザが起動し、ログイン・ワークスペース選択・consent を経てトークンを keychain (または XDG file) に保存します。他のツールが認証エラーを返したら、まずこのツールを呼んでください。force=true で既存トークンを破棄して再認証します。
Inputs: force.
download_fileAIdempotentInspect
generate_pdf_asyncで生成した単一PDFファイルをダウンロードします。requestIdとfileIdを指定し、ローカルファイルパスを返します。outputDir を指定するとそのディレクトリに、未指定の場合は現在の作業ディレクトリに保存します。
Inputs: requestId (required), fileId (required), fileName, outputDir.
download_zipAIdempotentInspect
generate_pdfs_asyncで生成したZIPファイルをダウンロードします。requestIdを指定し、ローカルのZIPファイルパスを返します。outputDir を指定するとそのディレクトリに、未指定の場合は現在の作業ディレクトリに保存します。
Inputs: requestId (required), fileName, outputDir.
generate_pdf_asyncAInspect
デザインIDとパラメータを指定してPDFを非同期生成します。即座にrequestIdとfiles情報を返します。ファイルのダウンロードはdownload_fileツールを使用してください。
【重要】呼び出し前に必ず get_design_parameters でデザインの必要パラメータ構造を確認し、ユーザーから必要な値を聞き出すこと。ユーザーが指定していないパラメータがある場合は、本ツールを呼ぶ前にユーザーに必ず確認すること。プレースホルダー値・架空の値を勝手に生成しないこと。パラメータが一切提供されていない場合も、まずユーザーに値を尋ねること。
Inputs: designId (required), version (required), content (required).
generate_pdfs_asyncAInspect
複数のパラメータセットでPDFを一括非同期生成します。即座にrequestIdとfiles情報を返します。ZIPダウンロードはdownload_zipツールを使用してください。
【重要】呼び出し前に必ず get_design_parameters でデザインの必要パラメータ構造を確認し、ユーザーから必要な値を聞き出すこと。ユーザーが指定していないパラメータがある場合は、本ツールを呼ぶ前にユーザーに必ず確認すること。プレースホルダー値・架空の値を勝手に生成しないこと。パラメータが一切提供されていない場合も、まずユーザーに値を尋ねること。
Inputs: designId (required), version (required), contents (required).
generate_pdfs_syncAInspect
複数のパラメータセットでPDFを一括同期生成し、ZIPファイルとして返します。生成完了後にZIPファイルのローカルパスを返します。outputDir を指定するとそのディレクトリに、未指定の場合はクライアントのワークスペース (Roots) または OS 一時ディレクトリに保存します。zipFileName で出力 ZIP のファイル名を指定可能 (デフォルト download.zip)。
【重要】呼び出し前に必ず get_design_parameters でデザインの必要パラメータ構造を確認し、ユーザーから必要な値を聞き出すこと。ユーザーが指定していないパラメータがある場合は、本ツールを呼ぶ前にユーザーに必ず確認すること。プレースホルダー値・架空の値を勝手に生成しないこと。パラメータが一切提供されていない場合も、まずユーザーに値を尋ねること。
Inputs: designId (required), version (required), contents (required), outputDir, +1 more.
generate_pdf_syncAInspect
デザインIDとパラメータを指定してPDFを生成します。応答にダウンロード URL が含まれるため、本ツール 1 回の呼び出しで結果提示が完結します (別途ダウンロード用ツールを呼ぶ必要はありません)。
stdio モード (Claude Desktop / Code): ローカルに保存し絶対パスも返します。outputDir で保存先を指定できます (未指定時はクライアントのワークスペース Roots または OS 一時ディレクトリ)。
HTTP モード (claude.ai / n8n 等): サーバー側には保存しません。includePreview=true を指定すると inline preview 用のバイナリも併せて返します (claude.ai が PDF preview をサポートしていない現状ではデフォルト false 推奨)。
【重要】呼び出し前に必ず get_design_parameters でデザインの必要パラメータ構造を確認し、ユーザーから必要な値を聞き出すこと。プレースホルダー値・架空の値を勝手に生成しないこと。
Inputs: designId (required), version (required), content (required), outputDir, +1 more.
get_design_parametersARead-onlyIdempotentInspect
デザインテンプレートのパラメータ構造を取得します。帳票生成に必要なパラメータの型・構造を確認できます。
Inputs: designId (required), version.
list_templatesARead-onlyIdempotentInspect
ワークスペース内のデザイン一覧を取得します。各デザインのID・名称・最新バージョン・サムネイルURLを返します。取得したidをdesignIdとしてPDF生成ツールやget_design_parametersに使用します。
Inputs: no named parameters.
suggest_paramsARead-onlyInspect
自然文の要件と designId からクライアント AI(Sampling)を使って generate_pdf_sync の params JSON を組み立てます。サーバー側 API キー不要。Sampling 未対応クライアントでは利用不可です。生成された params は内容確認のうえユーザーの承認を得てから generate_pdf_sync に渡してください。
Inputs: designId (required), description (required), version.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a clear, distinct purpose. Authentication is separate, sync vs async generators are clearly labeled, download tools are paired with async generators, and the helper tools (list_templates, get_design_parameters, suggest_params) are unique. No overlap.
All tool names follow a consistent verb_noun pattern in snake_case. Variations like generate_pdf_async vs generate_pdf_sync are systematic and predictable, making it easy to understand the tool's function from its name.
10 tools is an ideal size for this domain. It covers authentication, template exploration, parameter retrieval, PDF generation (sync/async, single/batch), downloading results, and smart param suggestion—all essential without unnecessary bloat.
The tool set provides a complete workflow for generating PDFs from templates: authenticate, list templates, get parameters, generate (sync or async, single or batch), and download. The inclusion of suggest_params adds convenience. No obvious gaps for the stated purpose.
Maintenance
Related MCP Connectors
LLM Orchestration MCP Agent
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Htmlpdf Transform Mcp connects AI agents to real public APIs via MCP. Tools include
Related MCP Servers
- AlicenseBqualityDmaintenanceMCP server that converts Markdown to high-quality PDF documents using LaTeX, enabling AI agents like Claude to generate professional PDFs without requiring sign-ups or credit cards.180 npm11MIT
- AlicenseNot gradedqualityCmaintenancePDF Tools AI - MCP server providing AI-powered tools and automation by MEOK AI Labs6 npmMIT
- AlicenseAqualityFmaintenanceMCP server for BulkRender — generate bulk DOCX and PDF documents from Claude, Cursor, Windsurf, and any MCP-compatible AI assistant1583 npm1MIT
- AlicenseAqualityCmaintenanceMCP server for generating professional PDFs from structured JSON in AI agents like Claude or Cursor, using pure Node.js with embedded fonts and precision text layout.624 npmMIT