Rossum MCP Server
OfficialProvides read-only access to serverless function hooks in Rossum, allowing AI agents to retrieve and analyze hooks and their source code.
Click on "Deploy 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., "@Rossum MCP Server show me all the queues in our organization"
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.
Rossum MCP Server
An MCP (Model Context Protocol) server that provides read-only access to Rossum API resources such as queues, schemas, serverless function hooks, and workspaces. This server allows AI agents to discover and utilize these Rossum functionalities as tools, in particular for analysis purposes.
SECURITY WARNING: MCP is not a mature environment from security perspective. Mixing third party MCP tools with untrusted files or LLM confusion may cause your API keys to be leaked if your MCP client has (direct or indirect) internet access. Use this MCP server at your own risk. If you use it, enable the MCP server only while solving pertinent tasks and leave it disabled otherwise.
NOTE: This MCP server is built for demo purposes. It (and its configuration) may randomly evolve in incompatible ways for the time being.
Setup
Ensure you have Python 3.10+ and uv installed.
Install dependencies:
uv syncConfigure the MCP server in your MCP client config (e.g., Claude Desktop, Windsurf, Cursor). Add this to your
mcp_config.json:{ "mcpServers": { "rossum": { "command": "uv", "args": ["--project=/path/to/rossum-mcp-server", "run", "mcp", "run", "/path/to/rossum-mcp-server/mcp_server.py"], "env": { "ROSSUM_API_KEY": "your_api_key_here", "ROSSUM_API_BASE": "https://api.elis.rossum.ai/v1" } } } }Replace
/path/to/rossum-mcp-serverwith the actual path to this project directory, andyour_api_key_herewith your actual Rossum API key.
Related MCP server: Swagger/OpenAPI MCP Server
Available MCP Tools
The server provides the following tools that AI agents can use:
rossum_get_queues - Get all queues from the Rossum organization
rossum_get_schema - Get a specific schema by its ID (requires
schema_idparameter)rossum_get_hooks - Get all serverless function hooks from the Rossum organization
rossum_get_hook - Get a specific hook by its ID including source code (requires
hook_idparameter)rossum_get_workspaces - Get all workspaces from the Rossum organization
rossum_get_workspace - Get a specific workspace by its ID (requires
workspace_idparameter)
Available Tools
6 toolsrossum_get_hookA
Get a specific serverless function hook by its ID, including its source code.
Args: hook_id: The ID of the hook to retrieve
Inputs: hook_id (required).
rossum_get_hooksB
Get all serverless function hooks from the Rossum organization.
Inputs: no named parameters.
rossum_get_queuesB
Get all queues from the Rossum organization.
Inputs: no named parameters.
rossum_get_schemaC
Get a specific schema by its ID.
Args: schema_id: The ID of the schema to retrieve
Inputs: schema_id (required).
rossum_get_workspaceC
Get a specific workspace by its ID.
Args: workspace_id: The ID of the workspace to retrieve
Inputs: workspace_id (required).
rossum_get_workspacesB
Get all workspaces from the Rossum organization.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose targeting different Rossum resources: hooks, queues, schemas, and workspaces. The singular vs. plural naming (e.g., get_hook vs. get_hooks) further clarifies whether the tool retrieves a specific item or all items, eliminating any ambiguity.
All tool names follow a consistent 'rossum_get_' prefix with snake_case, followed by the resource name (e.g., hook, hooks, queues, schema, workspace, workspaces). This predictable pattern makes it easy to understand what each tool does at a glance.
With 6 tools, the count is reasonable for a Rossum API server, covering key resources like hooks, queues, schemas, and workspaces. It's slightly lean but functional; adding a few more tools (e.g., for creating or updating resources) could enhance completeness without being excessive.
The toolset is severely incomplete as it only provides read operations (get) for resources. There are no tools for creating, updating, or deleting hooks, queues, schemas, or workspaces, which are essential for full CRUD coverage in a document processing platform like Rossum. This will cause significant agent failures when trying to modify data.
Maintenance
Related MCP Connectors
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that loads multiple OpenAPI specifications and exposes them to LLM-powered IDE integrations, enabling AI to understand and work with your APIs directly in development tools like Cursor.790MIT
- AlicenseDqualityDmaintenanceA Model Context Protocol server that enables LLMs to explore and interact with API specifications by providing tools for loading, browsing, and getting detailed information about API endpoints.414MIT
- AlicenseAqualityBmaintenanceA Model Context Protocol (MCP) server for accessing Productive.io API endpoints (projects, tasks, comments, todos), tailored for read-only operations, providing streamlined access to essential data while minimizing token consumption18MIT
- AlicenseNot gradedqualityDmaintenanceModel Context Protocol server that standardizes tool discovery, execution, and context management for AI applications.MIT