Atlas / MCP servers / 1xn-labs / 1xn AI Workflow Composer

1xn AI Workflow ComposerBLOCK

Name: 1xn AI Workflow Composer
Author: 1xn-labs

mcp/1xn-labs/1xn-ai-workflow-composer

MCP server by 1xn-labs · mcp · mcp server · model context protocol · Audited 2026-10-08

⚑ Report / re-scan Source ↗

vMCP - Virtual Model Context Protocol

Verdict

BLOCK

Grade

Trust score

60 /100

Exposed tools

153 142r · 11w · 0d

Transport

stdio · streamable-http

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/1xn-vmcp/) [](https://1xn.ai/docs/) [](https://1xn.ai)

Lego for AI workflows and agents: An open-source tool for composing, customizing and extending multiple MCP servers into a single logical, virtual MCP server

Built for fine grained context-engineering

Create vMCP, Add MCP servers and Fine-tune
Extend with your own prompts, tools and resources
Connect any client (Claude, ChatGPT, Gemini, Cursor, VScode, custom agents) to the vMCP
Create multiple logical vMCPs based on your workflow and agent needs

vMCP (virtual Model Context Protocol) is an AI configuration and management platform built on top of the Model Context Protocol. It is both :

A specification that builds on and extends MCPs: vMCP.json
A platform to create and deploy vMCP Servers:

Why We Built This

The Model Context Protocol has unlocked incredible possibilities for AI integrations, but users and developers quickly hit limitations:

Configuration Hell: Managing MCP configs across multiple clients (Claude, ChatGPT, VSCode, Cursor, Gemini) is tedious
Auth: Each mcp client needs its own auth for all the MCPs
Lack of Customization: Can't modify or extend existing MCPs for specific workflow needs - "context rot / confusion"
No Composition: Building complex workflows requires piecing together multiple tools from mult

Read from source at commit 83c836a6cbe7OBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add 1xn --env VMCP_DUMMY_USER_TOKEN=${VMCP_DUMMY_USER_TOKEN} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "1xn": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "VMCP_DUMMY_USER_TOKEN": "${VMCP_DUMMY_USER_TOKEN}"
      }
    }
  }
}

Exposed tools (153)

142 read · 11 write · 0 destructive.

Tool	Risk	Description
`a`	read	First number
`add`	write	Add two numbers
`add_numbers`	write	Add two numbers together.
`age`	read	Person age
`api_info_tool`	read	API information tool
`api_request_prompt`	read	Prompt using API configuration
`b`	read	Second number
`base_greeting`	read	Base greeting
`book_table`	read	Book a table with date availability check.
`calculate`	read	Perform calculations
`calculate_area`	read	Calculate circle area
`category`	read	Product category
`city`	read	City name
`complex_prompt_tool`	read	A complex prompt tool
`comprehensive_analysis`	read	Comprehensive analysis with all features
`comprehensive_reporter`	read	Comprehensive reporting tool
`contact_info_tool`	read	Provide contact information
`convert_time`	read	Convert time from one timezone to another.
`create_product`	write	Create a new product
`create_thumbnail`	write	Create a thumbnail from an image
`create_user`	write	Create a new user
`dashboard_analysis_prompt`	read	Analyze dashboard data
`data`	read	Dictionary data
`data_formatter`	read	Format data tool
`denominator`	read	Denominator
`description`	read	Product description
`details`	read	Additional details
`divide`	read	Divide two numbers
`echo_tool`	read	Echo tool
`email`	read	User email
`extended_greeting`	read	Extended greeting with base
`fetch_health`	read	Fetch health status
`fibonacci`	read	Calculate Fibonacci number
`first_name`	read	First name
`format`	read	Output format
`generate_poem`	read	Generate a poem using LLM sampling.
`get_config`	read	This returns unstructured output - no schema generated
`get_current_time`	read	Get current time in specified timezone.
`get_location`	read	Get location coordinates for a city using the world cities database.
`get_products_filtered`	read	Get filtered products
`get_server_health`	read	Get server health status
`get_statistics`	read	Get various statistics
`get_test_prompt`	read	Prompt for testing get operation
`get_user`	read	Get user profile - returns structured data
`get_user_by_id`	read	Get user by ID
`get_user_by_id_collection`	read	Get user by ID (from collection)
`get_user_profile`	read	Get user profile
`get_users`	read	Get Users (imported from collection)
`get_users_collection`	read	Get users (from collection)
`get_users_with_apikey`	read	Get users with API key
`get_users_with_config`	read	Get users using config API key
`get_weather`	read	Get weather for a city using Open-Meteo API.
`get_weather_array`	read	Get weather for multiple cities - returns structured data. Input should
`get_weather_json`	read	Get weather for multiple cities from JSON input. Each city can have location and unit settings.
`get_weather_structured`	read	Get weather for a city - returns structured data.
`greet_in_language`	read	Greet user in specific language
`greet_user`	read	Greet user with optional title
`greeting`	read	Standard greeting message
`greeting_tool`	read	Greeting tool
`health_check`	read	Health check endpoint from collection
`hello`	read	Say hello to someone.
`http_api_key_tool`	read	HTTP tool with API key
`http_basic_auth_tool`	read	HTTP tool with basic auth
`http_bearer_tool`	read	HTTP tool with bearer token
`http_config_sub_tool`	read	HTTP tool with config substitution
`http_get_tool`	read	A simple HTTP GET tool
`http_param_sub_tool`	read	HTTP tool with param substitution
`http_patch_tool`	write	HTTP PATCH tool
`http_post_tool`	write	HTTP POST tool with JSON body
`http_query_tool`	read	HTTP tool with query params
`id`	read	Resource ID
`input`	read	Input text
`input_data`	read	Input data
`items`	read	List of items
`language`	read	Language for greeting
`last_name`	read	Last name
`limit`	read	Result limit
`list_cities`	read	Get a list of cities
`location`	read	Location
`long_running_task`	write	Execute a task with progress updates.
`message`	read	Message to process
`multiply`	read	Multiply two numbers
`n`	read	Position in Fibonacci sequence
`name`	read	User
`new_price`	read	New price
`notify`	write	Send notification
`number`	read	Float number
`numbers`	read	List of numbers
`numerator`	read	Numerator
`operation`	read	Operation type
`param1`	read	Parameter 1
`param2`	read	Parameter 2
`personalized_greeting`	read	Personalized greeting
`personalized_report`	read	Generate personalized report
`price`	read	Product price
`process_data`	read	Process data with logging.
`product_id`	read	Product ID
`product_name`	read	Product name
`prompt_tool_1`	read	Prompt tool 1
`prompt_tool_2`	read	Prompt tool 2
`prompt_tool_with_config`	read	A prompt tool with config variables
`prompt_tool_with_mcp`	read	A prompt tool that calls MCP tools
`prompt_tool_with_vars`	read	A prompt tool with variables
`python_complex_tool`	read	Python tool with complex logic
`python_default_tool`	read	Python tool with default values
`python_dict_tool`	read	Python tool with dict parameter
`python_float_tool`	read	Python tool with float parameter
`python_list_tool`	read	Python tool with list parameter
`python_string_tool`	read	Python tool with string parameter
`query`	read	Search query
`query_db`	read	Tool that uses initialized resources.
`radius`	read	Circle radius
`report_type`	read	Type of report
`role`	read	User
`roll_dice`	read	Roll dice with specified number of dice and sides.
`search`	read	Search for information
`signature`	read	Email signature
`simple_analyzer`	read	A simple analysis tool
`simple_greeting`	read	A simple greeting prompt
`simple_prompt_tool`	read	A simple prompt tool
`simple_python_tool`	read	A simple Python tool
`string_formatter`	read	Format strings
`sum_list`	read	Sum a list of numbers
`sum_of_array`	read	Sum of array
`summary`	read	Summary text
`system_info_prompt`	read	System info prompt
`test_audio_content`	read	Tests audio content response
`test_elicitation`	read	Tests server-initiated elicitation (user input request)
`test_elicitation_sep1034_defaults`	read	Tests elicitation with default values for all primitive types (SEP-1034)
`test_embedded_resource`	read	Tests embedded resource content response
`test_error_handling`	read	Tests error response handling
`test_get_env`	read	Tests env setting for stdio servers
`test_get_headers`	read	Tests headers setting for sse/http servers
`test_image_content`	read	Tests image content response
`test_multiple_content_types`	read	Tests response with multiple content types (text, image, resource)
`test_prompt`	read	A test prompt
`test_sampling`	read	Tests server-initiated sampling (LLM completion request)
`test_simple_text`	read	Tests simple text content response
`test_tool`	read	A test tool
`test_tool_with_logging`	read	Tests tool that emits log messages during execution
`test_tool_with_progress`	read	Tests tool that reports progress notifications
`test_tools_change_notification`	read	Tests tool that emits log messages during execution
`text`	read	Text input
`title`	read	User
`update_product_price`	write	Update product price
`updates`	write	Update data
`user_id`	read	User ID
`user_name`	read	User
`username`	read	User name
`weather_analysis_prompt`	read	Analyze weather data
`weather_reporter`	read	Report weather tool
`x`	read	First number
`y`	read	Second number

Trust audit

BLOCKgrade F · trust 60/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	WARN
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (2 observation(s))
Network: declared (11 observation(s))
Shell: declared (1 observation(s))
Dependencies: not all pinned
Secrets in source: none-found

Findings (25)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95

frontend/src/lib/tsx-executor.tsx:180

componentFunction = new Function(...contextKeys, functionBody);

Why it matters. evaluates text as code

Fix. remove; use a parser or a dispatch table

MEDIUMInventory / provenance · inv.binary · CWE-1104

frontend/public/cursor.avif

cursor.avif

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

backend/src/vmcp/scripts/postgres_setup.py:38

print(f"VMCP_DATABASE_URL=postgresql://{user}:{password}@localhost:{port}/{database}")

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

backend/src/vmcp/server/middleware.py:552

logger.debug(f"🔍 MCP AUTH: Token length: {len(token)}")

MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532

backend/src/vmcp/server/vmcp_mcp_server.py:112

logger.debug(f"[VMCPServer] DEBUG: Extracted token: '{token[:20] if token else 'EMPTY'}...')")