How do I use Koncile MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Koncile MCP Server Upload this invoice and extract the data" 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.

Koncile MCP Server

by Koncile

Overview Schema Source Related Servers Discussions Admin

Python

Koncile MCP Server

An MCP (Model Context Protocol) server that wraps the Koncile public API, allowing AI assistants to interact with Koncile natively — upload documents, check extraction status, manage folders/templates/fields, and more.

Works with any MCP-compatible client: Claude Code, Claude Desktop, Cursor, Windsurf, Cline, and others.

Quickstart

No installation needed — connect directly to the hosted server with your API key:

# Claude Code
claude mcp add --transport http koncile https://mcp.koncile.ai/mcp \
  --header "Authorization: Bearer your-api-key"

For other MCP clients, use the URL https://mcp.koncile.ai/mcp with your API key as a Bearer token in the Authorization header.

Related MCP server: Doc2x MCP Server

Local installation

# From source
git clone https://github.com/Koncile/koncile-mcp.git
cd koncile-mcp
pip install -e .

# Or directly
pip install koncile-mcp

Configuration

The server needs a KONCILE_API_KEY to authenticate with the Koncile API. You can provide it in two ways:

Option 1: Config file (recommended)

Create ~/.config/koncile/config:

mkdir -p ~/.config/koncile
echo "KONCILE_API_KEY=your-api-key" > ~/.config/koncile/config
chmod 600 ~/.config/koncile/config

Option 2: Environment variable

export KONCILE_API_KEY=your-api-key

Environment variables take precedence over the config file.

Claude Code

claude mcp add --transport stdio koncile -- koncile-mcp

If using the environment variable approach instead of the config file:

claude mcp add --transport stdio -e KONCILE_API_KEY=your-api-key koncile -- koncile-mcp

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "koncile": {
      "command": "koncile-mcp"
    }
  }
}

If using the environment variable approach instead of the config file:

{
  "mcpServers": {
    "koncile": {
      "command": "koncile-mcp",
      "env": {
        "KONCILE_API_KEY": "your-api-key"
      }
    }
  }
}

Available Tools (24 total)

Core Document Workflow

Tool	Description
`upload_file`	Upload a file (via local path or base64) for extraction. Returns task IDs.
`get_task_status`	Poll processing status of an upload task.
`list_documents`	List document IDs, optionally filtered by date range.
`get_document_data`	Get extracted fields and line items for a document.
`list_folders`	List all folders with their templates.

Folder Management

Tool	Description
`get_folder`	Get folder details and templates.
`create_folder`	Create a new folder.
`update_folder`	Update folder name/description.
`delete_folder`	Delete a folder.

Template Management

Tool	Description
`get_template`	Get template details, field IDs, instruction IDs.
`create_template`	Create a new template (optionally duplicate from existing).
`update_template`	Update template name/description.
`delete_template`	Delete a template.

Field Management

Tool	Description
`get_field`	Get field details.
`create_field`	Create a field (type: "General fields" or "Line fields").
`update_field`	Update field properties.
`delete_field`	Delete a field.

Instruction Management

Tool	Description
`get_instruction`	Get instruction details.
`create_instruction`	Create an instruction for a template.
`update_instruction`	Update instruction content/type.
`delete_instruction`	Delete an instruction.

Utilities

Tool	Description
`check_api_key`	Verify API key validity.
`download_file`	Download original file (returns base64).
`delete_document`	Delete a document.

Example Workflow

A typical document extraction workflow:

Upload: Use upload_file with a local file path (or base64-encoded content) → get task_id
Poll: Call get_task_status with task_id until status is DONE
Read: Use get_document_data to retrieve extracted fields and line items

User: Upload this invoice and extract the data
Claude: [calls upload_file with file_path="/path/to/invoice.pdf"] → task_id: "abc-123"
Claude: [calls get_task_status] → status: "PROCESSING"
Claude: [calls get_task_status] → status: "DONE", document_id: 42
Claude: [calls get_document_data] → General_fields: {vendor: "Acme", total: "1,234.56"}, Line_fields: [...]

Self-hosting

You can run the MCP server as your own HTTP service:

# Run the HTTP server (default: 0.0.0.0:8080)
koncile-mcp-server

# Custom host/port
HOST=127.0.0.1 PORT=3000 koncile-mcp-server

# Or via Docker
docker build -t koncile-mcp .
docker run -p 8080:8080 -e KONCILE_API_URL=https://api.koncile.ai koncile-mcp

Clients authenticate with their Koncile API key as a Bearer token:

claude mcp add --transport http koncile https://your-host:8080/mcp \
  --header "Authorization: Bearer your-api-key"

Development

pip install -e ".[dev]"
pytest

Testing with MCP Inspector

KONCILE_API_KEY=your-key \
  npx @modelcontextprotocol/inspector koncile-mcp

# Or against local dev API:
KONCILE_API_URL=http://localhost:8000 KONCILE_API_KEY=your-key \
  npx @modelcontextprotocol/inspector koncile-mcp

License

MIT

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

ragie
com.mcparmory
Ingest, manage, and retrieve documents for RAG-powered AI applications
RAG Systems Databases Knowledge & Memory
2
QCDatabase.AIOAuth
ai.qcdatabase
Connects AI assistants to QCDatabase.AI for everyday construction quality-control work.
Databases Project Management
1
mcpOAuth
com.keboola
Connect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...
Data Platforms Databases Developer Tools
286
Iteration Layer AOAuth
com.iterationlayer
Composable APIs for document extraction, image transformation, and document & sheet generation.
App Automation Image & Video Processing Multimedia Processing
2

Related MCP Servers

SourceSync.ai MCP Server
Knowledge & Memory RAG Systems Content Management Systems
sitegpt
A
license
B
quality
D
maintenance
Allows AI models to interact with SourceSync.ai's knowledge management platform to organize, ingest, retrieve, and search content in knowledge bases.
Updated 2 years ago (2025-03-09 01:48 UTC)
25
11 npm
3
MIT
Doc2x MCP Server
Documentation Access File Systems App Automation
NoEdgeAI
A
license
A
quality
D
maintenance
Enables AI assistants to parse and convert PDFs and images to structured text formats using the Doc2x v2 API. Supports asynchronous document processing, format conversion, and file downloads with configurable polling and timeout settings.
Updated 3 months ago (2026-06-22 05:13 UTC)
13
30 npm
3
MIT
Upstage MCP Server
AI & Machine Learning Data Platforms
PritamPatil2603
A
license
A
quality
C
maintenance
Enables AI assistants to extract and structure content from documents (PDFs, images, Office files) using Upstage AI's document digitization and information extraction APIs.
Updated a year ago (2025-04-17 03:52 UTC)
2
3
MIT
Context11 MCP Server
Knowledge & Memory Search Note Taking
vedadsose
A
license
B
quality
D
maintenance
Enables AI assistants to search, retrieve, and manage documents from a Context11 knowledge base through tools like search_context, get_document, and list_folders.
Updated 8 months ago (2026-01-23 14:11 UTC)
6
5 npm
MIT

Koncile MCP Server

Quickstart

Local installation

Configuration

Option 1: Config file (recommended)

Option 2: Environment variable

Claude Code

Claude Desktop

Available Tools (24 total)

Core Document Workflow

Folder Management

Template Management

Field Management

Instruction Management

Utilities

Example Workflow

Self-hosting

Development

Testing with MCP Inspector

License

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

SourceSync.ai MCP Server

Doc2x MCP Server

Upstage MCP Server

Context11 MCP Server