WorkflowsBLOCK
orchestrate & combine prompts + MCP servers into compound MCP tools
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
mcpn.ai helps you create, organize, and share AI workflows and prompts. Like a dynamic prompt library you can share & version across MCP tools and servers for specific tasks.
Created by
Usage
Basic Example
plan_prd: description: "Create a product requirements..." prompt: | You are an expert product manager/business analyst and are now entering "PRD Mode" Begin by deeply reflecting upon the notes, requirements and images provided... tools: createPRD, createStoriesFromPRD, createRoadmap coding_max: description: "Highly effective Coding Agent" prompt: | You are now entering "Developer Mode" - deeply reflect upon the changes being asked and analyze existing code to map the full scope... tools: getConsoleLogs, getErrorLogs, getLinter ...
315b206a21baOBSERVED · 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 test-utils -- npx -y @mcpn/[email protected]
{
"mcpServers": {
"test-utils": {
"command": "npx",
"args": [
"-y",
"@mcpn/[email protected]"
]
}
}
}Exposed tools (13)
11 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add | write | Add a workflow preset: from built-in names or a giget source. |
advanced_configuration | read | Configure a system with complex parameters |
calculator | read | Perform mathematical calculations |
config | read | Manage MCPN configuration. |
generate_thought | read | Test generate_thought parameters |
get | read | Display the resolved MCPN configuration. |
init | read | Initialize MCPN in the current project |
placeholder | read | This is a placeholder tool when no other tools are loaded |
server | write | Start the MCP server process |
template_calculator | read | Calculator with template parameters |
tool1 | read | Description 1 |
tool2 | read | Description 2 |
tool3 | read | Description 3 |
Trust audit
BLOCKgrade F · trust 44/100 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 | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- declared (9 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (18)
const config = yaml.load(content) as PresetConfig;
const config = yaml.load(content) as PresetConfig;
const fileConfig = yaml.load(content) as DevToolsConfig;
const fileConfig = yaml.load(content) as DevToolsConfig;
const config = yaml.load(content) as DevToolsConfig;
.navigation.yml
: "../../bin/mcpn.mjs",
const cliEntryPointPath = path.resolve(__dirname, '../../../packages/cli/bin/mcpn.mjs');
@iconify-json/lucide, @iconify-json/simple-icons, @iconify-json/vscode-icons, @nuxt/content, @nuxt/image, nuxt, nuxt-og-image, @nuxt/eslint
@cloudflare/workers-types, @release-it/bumper, @release-it/conventional-changelog, @types/json-query, @types/pg, @vitejs/release-scripts, conventional-changelog-cli, cursor-tools
rollup-plugin-visualizer
@anthropic-ai/sdk, mri, openai, pathe, ts-node
@nuxt/fonts, @nuxtjs/tailwindcss, nuxt, tailwindcss, vue-router
Gates applied: no_behavioural_pass.
315b206a21bafull audit observations/trust-audit/mcp-server/dx-zero__workflows-2.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 | 315b206a21ba | BLOCK | F | 44 | first audit |
Questions
What is the Workflows MCP server?
orchestrate & combine prompts + MCP servers into compound MCP tools
What tools does Workflows expose?
13 in total: 11 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Workflows safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (44/100) and found 10 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
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 @mcpn/test-utils at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (315b206a21ba), read on 2026-10-08. The repository is watched and re-audited when it changes.