flexorch-mcp
OfficialThis server connects MCP-compatible AI agents to the FlexOrch document intelligence platform, enabling end-to-end document processing, data extraction, and dataset export through natural language tool calls. It provides 6 tools:
document.process: Upload and process documents (PDF, DOCX, TXT, XLSX, HTML, XML, EML, JPG, PNG, TIFF) from a public URL — performs automatic classification, structured field extraction, PII detection/masking, and quality scoring.job.status: Monitor asynchronous processing jobs (document processing or dataset builds) until they complete or fail.job.result: Retrieve structured extraction results from a completed job, including document type, detected language, quality grade (A–D), PII summary, and extracted field values.dataset.build: Package extracted records from a completed document execution into a named, structured dataset.dataset.search: Search across indexed datasets using structured, semantic, or hybrid modes, with filtering by document type, language, and quality grade. Semantic/hybrid modes require a Pro+ plan.dataset.export: Export a complete dataset as JSONL, CSV, JSON, Markdown, XML, or RAG chunks (LangChain/LlamaIndex compatible) for LLM fine-tuning or downstream use.
Allows OpenAI Codex to process documents, extract structured data, detect PII, and export datasets via MCP tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@flexorch-mcpProcess the latest invoice PDF and extract vendor name and total amount."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
flexorch-mcp
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.
Related MCP server: MinerU Document Explorer
Tools
Tool | Description |
| Upload and process a document (PDF, DOCX, TXT, XLSX, HTML, XML, EML, JPG, PNG, TIFF) |
| Poll a processing job until completed or failed |
| Get structured extracted fields from a completed job |
| Build a structured dataset from a completed execution |
| Semantic search across indexed datasets (Pro+) |
| Export a dataset as JSONL, CSV, JSON, XML, MD, or RAG (LangChain/LlamaIndex chunks) |
Installation
pip install flexorch-mcpRequires Python 3.10+.
Configuration
Claude Desktop
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"flexorch": {
"command": "flexorch-mcp",
"env": {
"FLEXORCH_API_KEY": "dfx_your_key_here"
}
}
}
}Cursor
Add to your Cursor MCP config:
{
"flexorch": {
"command": "flexorch-mcp",
"env": {
"FLEXORCH_API_KEY": "dfx_your_key_here"
}
}
}OpenAI Codex
Add to ~/.codex/config.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
flexorch-mcp --check
# → FlexOrch API key: dfx_xxx*** ✓
# → Connection: OK (api.flexorch.com)
# → Plan: Starter (1,200 credits/mo)
# → Tools: 6 registeredExample 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 contentPlan limits
All FlexOrch plan limits apply to MCP tool calls. Credits are consumed per document processed.
Plan | Credits/mo | Semantic search |
Trial | 1,200 (30 days) | — |
Starter | 1,200 | — |
Pro | 6,000 | ✓ |
Enterprise | Custom | ✓ |
Security
API key is read from the
FLEXORCH_API_KEYenvironment variable — never passed as a tool argumentNo 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.comuses HTTPS
Related
flexorch-audit — Standalone PII detection and document quality scoring (no account required)
flexorch-sdk — Python SDK for developers
flexorch-sdk-js — TypeScript SDK for developers
docs.flexorch.com — Full documentation
License
MIT — see LICENSE.
Maintenance
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/flexorch/flexorch-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server