list_workflowsLABSCO SUMMARY
Workflows that get rewritten from their own run history.
The unusual pairing is optimisation next to backtesting: a workflow's prompts can be rewritten based on how its runs went, and a strategy can be swept across parameter variations before anything goes live.
What it is
An MCP server for Vynn, a platform for AI workflows that tune themselves. Beyond creating and running workflows it exposes the optimisation loop — prompt rewriting and model recommendations — plus a separate backtesting set for trading strategies.
What you get
- Workflows listed, inspected step by step, created and run
- Run history and per-run summaries
- Prompt optimisation for a single step, and the optimised prompt applied
- Model swap recommendations
- Cron schedules and inbound webhook triggers
- Backtests from natural-language or structured strategies, parameter sweeps, and mean-variance portfolio optimisation
- Workflow templates to clone, the tools attachable to a step, and performance analytics
Requirements
pip install vynn-mcp and a Vynn API key in VYNN_API_KEY. Keys are issued on signup at the-vynn.com and free-tier keys start with vynn_free_.
Setup effort
One command plus a key — pip install vynn-mcp, then supply credentials
USE CASES
01
Getting a workflow running on a schedule
Create it, run it once to check, then set the cron schedule.
02
Fixing a step that keeps producing weak output
Ask for a prompt optimisation on that step, read it, then apply it.
03
Working out whether a cheaper model would do
Get a model swap recommendation for the workflow.
04
Testing a trading idea before risking anything
Describe the strategy in words, backtest it, then sweep the parameters.
05
Finding out why last night's run failed
Read the run history and open the run in question.
06
Starting from something that already works
List the templates, and list the tools a step can attach to.
21 tools
Listed in project docs. Your client may show a different list.
get_workflowcreate_workflowrun_workflowget_runsget_run_summaryoptimize_promptapply_prompt_optimizationget_model_recommendationset_scheduleget_scheduledelete_schedulecreate_triggerlist_triggersbacktestbatch_backtestoptimize_portfoliolist_templatesclone_templatelist_available_toolsget_analyticsBEFORE YOU INSTALL
What to know first
Tools you get
21 tools named in the project's documentation.
Requires
- vynn-mcp on PATH
- VYNN_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install vynn-mcpMCP Clients
Claude Code, Cursor
JSON
{
"mcpServers": {
"vynn": {
"command": "vynn-mcp",
"env": {
"VYNN_API_KEY": "<YOUR_VYNN_API_KEY>"
}
}
}
}
