Workflows MCP Server

MCP server for DAG-based workflow execution with YAML definitions and LLM collaboration

Local serverstdioPython

What is the Workflows MCP server?

MCP server for DAG-based workflow execution with YAML definitions and LLM collaboration. The workflows mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 2 defined tools rather than through you.

What it actually does

Run YAML workflows as MCP tools so agents can automate real tasks with one server.

  • Define tasks once in YAML and run them from any MCP-compatible client
  • Orchestrate multi-step work with dependency-aware execution
  • Support interactive runs (Prompt blocks) with pause/resume
  • Keep secrets server-side via WORKFLOW_SECRET_* with redacted outputs
  • Run synchronous or async jobs with queue visibility and cancellation

Its toolset

Everything the assistant can do here goes through one of these:

  • Prerequisites — The Prerequisites tool exposed by this server
  • Configuration — The Configuration tool exposed by this server

Configuration

You will need 8 environment variables: WORKFLOWS_TEMPLATE_PATHS, WORKFLOWS_LOG_LEVEL, WORKFLOW_SECRET_API_KEY, MEMORY_DB_HOST, MEMORY_DB_PORT, MEMORY_DB_NAME, MEMORY_DB_USER, MEMORY_DB_PASSWORD. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • PostgreSQL 13 or later, network-accessible from the server process. - A database user with CREATE DATABASE rights on the admin database (typically postgres) if auto-create is enabled, or a pre-existing database that the user can connect to.

Adding it to your client

The server ships on PyPI as workflows-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Workflows's toolset — Prerequisites, Configuration — is a fair guide to whether it matches your workflow.

This entry was verified against Workflows's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the workflows mcp server does with a few real requests.

Available tools

ToolWhat it does
PrerequisitesThe Prerequisites tool exposed by this server.
ConfigurationThe Configuration tool exposed by this server.

How to install the Workflows MCP server

If installed with `pip`:

```json
{
  "mcpServers": {
    "workflows": {
      "command": "workflows-mcp",
      "env": {
        "WORKFLOWS_TEMPLATE_PATHS": "/path/to/your/workflows",
        "WORKFLOWS_LOG_LEVEL": "INFO",
        "WORKFLOW_SECRET_API_KEY": "your-secret-value"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • PostgreSQL 13 or later, network-accessible from the server process. - A database user with CREATE DATABASE rights on the admin database (typically postgres) if auto-create is enabled, or a pre-existing database that the user can connect to.
VariableDescriptionRequired
WORKFLOWS_TEMPLATE_PATHSFilesystem location the server is allowed to use.Optional
WORKFLOWS_LOG_LEVELConfiguration value read at startup.Optional
WORKFLOW_SECRET_API_KEYCredential the server authenticates with.Yes
MEMORY_DB_HOSTEndpoint or connection string the server talks to.Optional
MEMORY_DB_PORTConfiguration value read at startup.Optional
MEMORY_DB_NAMEConfiguration value read at startup.Optional
MEMORY_DB_USERConfiguration value read at startup.Optional
MEMORY_DB_PASSWORDConfiguration value read at startup.Optional

Example prompts to try

  • Use Workflows to Prerequisites.
  • Use Workflows to Configuration.

Frequently asked questions

It connects Workflows to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (Prerequisites, Configuration) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Workflows directly.