WorkflowsSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🤖 Co-authored with [Claude Code](https://claude.ai/referral/uralRLy1tw) - Building workflows so LLMs can finally follow a recipe without burning the kitchen! 🔥
A powerful Model Context Protocol (MCP) implementation that enables LLMs to execute complex, multi-step workflows with cognitive actions and tool integrations.
🌟 Overview
workflows-mcp transforms how AI assistants handle complex tasks by providing structured, reusable workflows that combine tool usage with cognitive reasoning. Instead of ad-hoc task execution, workflows provide deterministic, reproducible paths through multi-step processes.
🚀 Key Features
- 📋 Structured Workflows: Define clear, step-by-step instructions for LLMs
- 🧠 Cognitive Actions: Beyond tool calls - analyze, consider, validate, and reason
- 🔀 Advanced Control Flow: Branching, loops, parallel execution
- 💾 State Management: Track variables and results across workflow steps
- 🔍 Comprehensive Validation: Ensure workflow integrity before execution
- 📊 Execution Tracking: Monitor success rates and performance metrics
- 🛡️ Type-Safe: Full TypeScript support with Zod validation
- 🎯 Dependency Management: Control variable visibility to reduce token usage
- ⚡ Performance Optimized: Differential updates and progressive step loading
📦 Installation
Using npx (recommended)
npx @fiveohhwon/workflows-mcp
From npm
npm install -g @fiveohhwon/workflows-mcp
From Source
git clone https://github.com/FiveOhhWon/workflows-mcp.git cd workflows-mcp npm install npm run build
🏃 Configuration
Claude Desktop
Add this configuration to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
Using npx (recommended):
{
"mcpServers": {
"workflows": {
"command": "npx",
"args": ["-y", "@five0ce3a9497405OBSERVED · 2026-10-08Connect
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.
claude mcp add workflows-mcp -- npx -y @fiveohhwon/[email protected]
{
"mcpServers": {
"workflows-mcp": {
"command": "npx",
"args": [
"-y",
"@fiveohhwon/[email protected]"
]
}
}
}Exposed tools (9)
5 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
create_workflow | write | Create a new workflow with specified steps and configuration. WORKFLOW STRUCTURE: - name: Descriptive workflow name - description: What the workflow accomplishes - goal: The end result or outcome - version: Semantic version (default: |
delete_workflow | destructive | Soft delete a workflow (can be recovered) |
get_workflow | read | Get a specific workflow by ID |
get_workflow_versions | read | List all available versions of a workflow |
list_workflows | read | List all workflows with optional filtering and sorting |
rollback_workflow | read | Rollback a workflow to a previous version |
start_workflow | write | Start a workflow execution session with step-by-step control |
temp-name | read | temp |
update_workflow | write | Update an existing workflow with optional version increment |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
delete_workflow
@modelcontextprotocol/sdk, uuid, zod, @types/node, @types/uuid, tsx, typescript
Gates applied: no_behavioural_pass.
0ce3a9497405full audit observations/trust-audit/mcp-server/fiveohhwon__workflows-4.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 0ce3a9497405 | SAFE | B | 89 | first audit |
Questions
What tools does Workflows expose?
9 in total: 5 read-only, 3 that write, and 1 that can delete or overwrite (delete_workflow). Every one is listed on this page with its risk.
Is Workflows safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Workflows need?
No credential environment variables were found in its source, so it appears to need none.
How does Workflows run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @fiveohhwon/workflows-mcp at 0.3.3.
How current is this page?
The grade is for one exact copy of the source (0ce3a9497405), read on 2026-10-08. The repository is watched and re-audited when it changes.