FlexOrch

io.github.dev-flexorchPublished by GitHub account dev-flexorchv0.1.2Updated Oct 24, 2026

Classify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & MemoryData & Analytics

Overview

AI-generated overview

FlexOrch MCP proxy that lets an assistant process documents, extract structured fields, mask PII and export JSONL or RAG datasets.

What you can do
  • Upload and process documents (PDF, DOCX, TXT, XLSX, HTML, XML, EML, JPG, PNG, TIFF) and re-queue existing ones
  • Poll processing jobs and retrieve structured extracted fields from completed jobs
  • Build datasets from completed executions and export them as JSONL, CSV, JSON, XML, MD or RAG chunks
  • Index datasets for semantic vector search and retrieve paginated RAG-ready chunks (Pro plan and above)
When to use it
Useful when you want an assistant to turn invoices, forms or other documents into structured data and LLM-ready datasets without writing code, especially for fine-tuning or RAG preparation.
Requirements
Local Python package (Python 3.10+) run over stdio, configured in Claude Desktop, Cursor or Codex. A FlexOrch account and API key supplied through the FLEXORCH_API_KEY environment variable; network access to the FlexOrch API.
Before you install
Document contents are uploaded to FlexOrch's managed infrastructure for processing, so data leaves your machine. Processing consumes plan credits per document, and semantic search, indexing and chunk retrieval require a Pro or higher plan. The API key is a secret read from FLEXORCH_API_KEY.

Installation

In SourceWeft

  1. Open FlexOrch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

flexorch-mcp

[smithery badge] [PyPI version] [CI] [License: MIT] [Python 3.10+] [flexorch-mcp MCP server] [Glama score]

MCP server for FlexOrch — SDK for machines.

Connect Claude and other MCP-compatible agents to the FlexOrch document intelligence pipeline. Process documents, extract structured data, detect PII, and export LLM-ready datasets — all through natural language tool calls.

What this is

flexorch-mcp is a thin proxy that exposes the FlexOrch API as MCP tools. All processing happens on FlexOrch's managed infrastructure. A FlexOrch account and API key are required.

For humans writing code: use flexorch-sdk (Python) or flexorch-sdk-js (TypeScript).
For agents: use this package.

Tools

ToolDescription
document.processUpload and process a document (PDF, DOCX, TXT, XLSX, HTML, XML, EML, JPG, PNG, TIFF)
document.reprocessRe-queue an already-uploaded document through the pipeline
job.statusPoll a processing job until completed or failed
job.resultGet structured extracted fields from a completed job
dataset.buildBuild a structured dataset from a completed execution
dataset.searchSemantic search across indexed datasets (Pro+)
dataset.exportExport a dataset as JSONL, CSV, JSON, XML, MD, or RAG (LangChain/LlamaIndex chunks)
dataset.indexTrigger semantic vector indexing for a dataset (Pro+)
dataset.chunksRetrieve paginated RAG-ready text chunks from an indexed dataset (Pro+)

Installation

bash
pip install flexorch-mcp

Requires Python 3.10+.

Configuration

Claude Desktop

Add to your Claude Desktop config file (create it if it doesn't exist):

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
json
{  "mcpServers": {    "flexorch": {      "command": "flexorch-mcp",      "env": {        "FLEXORCH_API_KEY": "dfx_your_key_here"      }    }  }}

Cursor

Add to your Cursor MCP config:

json
{  "flexorch": {    "command": "flexorch-mcp",    "env": {      "FLEXORCH_API_KEY": "dfx_your_key_here"    }  }}

OpenAI Codex

Add to ~/.codex/config.toml:

toml
[mcp_servers.flexorch]command = "uvx"args = ["flexorch-mcp"]
[mcp_servers.flexorch.env]FLEXORCH_API_KEY = "dfx_your_key_here"

Get your API key from app.flexorch.com/settings.

Verify connection

bash
flexorch-mcp --check# → FlexOrch API key: dfx_xxx*** ✓# → Connection: OK (api.flexorch.com)# → Plan: Starter (1,200 credits/mo)# → Tools: 9 registered

Example agent workflow

User: "Process this invoice and export it as JSONL for fine-tuning."
Agent:  1. document.process(file_url="https://...")   → job_id: 1234  2. job.status(1234)                           → completed, execution_id: 567  3. job.result(567)                            → vendor, total, date, PII masked  4. dataset.build(execution_id=567)            → job_id: 1235  5. job.status(1235)                           → completed, dataset_id: 89  6. dataset.export(89, format="jsonl")         → inline JSONL content

Plan limits

All FlexOrch plan limits apply to MCP tool calls. Credits are consumed per document processed.

PlanCredits/moSemantic search
Trial1,200 (30 days)—
Starter1,200—
Pro6,000✓
EnterpriseCustom✓

Security

  • API key is read from the FLEXORCH_API_KEY environment variable — never passed as a tool argument
  • No data is stored or cached by this server — stateless proxy
  • PII masking is applied by FlexOrch's pipeline before results are returned
  • All communication with api.flexorch.com uses HTTPS

Related

License

MIT — see LICENSE.

Source: README.md at commit 2276a4b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts