New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Harness MCP Scan

by ruvnet in ruvnet/ruflo

Static security scan of a harness's declared MCP surface via harness mcp-scan {path}.

MITAuto-check: notesAgent Workflows

Install Harness MCP Scan

skills CLI
$ npx skills add ruvnet/ruflo --skill harness-mcp-scan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ruvnet/ruflo harness-mcp-scan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ruflo-metaharness/skills/harness-mcp-scan .claude/skills/harness-mcp-scan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
harness-mcp-scan
GitHub stars
74k
Token cost
~429 tokens
SKILL.md length
155 words
Files
1
Skills in repo
265
Repo updated
First seen
Licence
MIT

At a glance

Static security scan of a harness's declared MCP surface via harness mcp-scan {path}.

  • Works in 4 steps: Invoke the pinned harness binary… → Parse findings[] with { severity, id,… → fail-on : exit 1 when any finding is at… → …
  • Tasks that involve MCP servers
  • SKILL.md covers Algorithm, Severity rank, CI integration and Graceful degradation
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Harness MCP Scan is an agent skill from ruvnet/ruflo. Static security scan of a harness's declared MCP surface via harness mcp-scan {path}. Reads .mcp/servers.json + .harness/claims.json. Pure-read, no dispatch. Exits 1 on findings at or above --fail-on severity.

Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers and Security review. It works with Model Context Protocol. The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers
  • Tasks that involve Security review

Example prompts

  • “/harness-mcp-scan”

Requirements

  • Pre-approved tools (allowed-tools): Bash

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Invoke the pinned harness binary (metaharness@~0.4.1, resolved from a
  2. Parse findings[] with { severity, id, server, tool, message }.
  3. fail-on : exit 1 when any finding is at or above that
  4. Output JSON (default) or markdown table.

What it can do on your machine

Read from SKILL.md and the folder at commit 6c04654. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Harness MCP Scan loads about 429 tokens when it runs. Until then it costs about 59 tokens; SKILL.md has 155 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~59
When it runs · the whole SKILL.md, loaded when a task matches
~429

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit 6c04654, republished under its MIT licence (© ruvnet). 155 words, ~429 tokens.

Download SKILL.mdSave it as .claude/skills/harness-mcp-scan/SKILL.md (or your agent's skills folder).
name
harness-mcp-scan
description
Static security scan of a harness's declared MCP surface via `harness mcp-scan {path}`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
allowed-tools
Bash
argument-hint
[--path .] [--fail-on low|medium|high] [--format table|json]

Calls harness mcp-scan to enumerate every declared MCP server + tool and flag policy / permission / dependency issues. Never executes any tool; pure static analysis.

Algorithm

Implementation: scripts/mcp-scan.mjs.

  1. Invoke the pinned harness binary (metaharness@~0.4.1, resolved from a local install or the one-time ~/.ruflo/metaharness-cache-<pin> cache — never @latest): harness mcp-scan <path> --json.
  2. Parse findings[] with { severity, id, server, tool, message }.
  3. --fail-on <severity>: exit 1 when any finding is at or above that level. Default high.
  4. Output JSON (default) or markdown table.

Severity rank

SeverityRank
low1
medium2
high3

--fail-on high (default) only fails on HIGH; --fail-on medium also fails on MEDIUM; --fail-on low fails on any finding.

CI integration

yaml
- name: MCP static scan
  run: node plugins/ruflo-metaharness/scripts/mcp-scan.mjs --fail-on high

The exit code is the only thing CI watches; the JSON output goes to artifacts for human review.

Graceful degradation

When harness binary is unavailable (no network, blocked registry), emits structured { degraded: true, reason: 'metaharness-not-available' } and exits 0. Ruflo continues — ADR-150 architectural constraint.

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/ruflo-metaharness/skills/harness-mcp-scan of ruvnet/ruflo.

Open the folder on GitHubat commit 6c04654

Compare with similar skills

Harness MCP Scan next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Harness MCP Scan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Harness MCP Scan this skillruvnet/ruflo74k—~429Automated safety check: NotesMIT
Security Scanaffaan-m/ECC276k5 repos~1.1kAutomated safety check: PassMIT
Flow SwarmLeoYeAI/openclaw-master-skills2.2k—~5.3kAutomated safety check: PassMIT
MCP Security Auditboshi-xixixi/TraeSkill276—~2.2kAutomated safety check: PassMIT
Keeljoseconti/declaracion-renta-espana190—~11kAutomated safety check: WarnGPL-3.0-or-later
MCP Server Security Auditawarexone/Agentic-Bug-Hunter5.3k—~1.9kAutomated safety check: WarnMIT

Similar skills

  • Security Scan

    affaan-m/ECC

    Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

    276k GitHub starsUsed in 5 repos~1.1k tokens
    Agent WorkflowsAuto-check passed

  • Flow Swarm

    LeoYeAI/openclaw-master-skills

    Multi-agent swarm orchestration via RuFlo + Claude Code. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~5.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • MCP Security Audit

    boshi-xixixi/TraeSkill

    Audit MCP (Model Context Protocol) server configurations for security issues.

    276 GitHub stars~2.2k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Keel

    joseconti/declaracion-renta-espana

    A skill your agent uses for ANY new software project from idea to release — websites, WordPress/WooCommerce plugins, MCP servers, web apps, components, or libraries.

    190 GitHub stars~11k tokensUpdated 2 mo ago
    SecurityAuto-check: warnings

  • MCP Server Security Audit

    awarexone/Agentic-Bug-Hunter

    Audits MCP servers and their client configs for tool poisoning, prompt injection, over-privileged tools, injection bugs, secret leaks and missing approval gates.

    5.3k GitHub stars~1.9k tokensUpdated yesterday
    SecurityAuto-check: warnings

  • MCP Security Audit

    github/awesome-copilot

    Official

    Audit MCP (Model Context Protocol) server configurations for security issues.

    40k GitHub stars~3.1k tokensUpdated yesterday
    SecurityAuto-check passed

More from ruvnet/ruflo

All 265 skills in this repo

  • AgentDB Pattern Memory

    ruvnet/ruflo

    Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed

  • Security Audit Scanner

    ruvnet/ruflo

    Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed

  • SPARC Development Methodology

    ruvnet/ruflo

    Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed

  • Swarm Orchestration

    ruvnet/ruflo

    Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Auto-check passed

  • Ruflo Multi-Agent Orchestration

    ruvnet/ruflo

    Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed

  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

Works with

Categories

Questions about Harness MCP Scan

What does Harness MCP Scan do?

Static security scan of a harness's declared MCP surface via harness mcp-scan {path}. Harness MCP Scan is an agent skill from ruvnet/ruflo. Static security scan of a harness's declared MCP surface via harness mcp-scan {path}.

When should I use Harness MCP Scan?

Harness MCP Scan fits situations like: tasks that involve MCP servers; tasks that involve Security review.

How do I install Harness MCP Scan in Claude Code?

Run `npx skills add ruvnet/ruflo --skill harness-mcp-scan -a claude-code`. Or copy the skill folder (plugins/ruflo-metaharness/skills/harness-mcp-scan in ruvnet/ruflo) into .claude/skills/harness-mcp-scan in your project. Claude Code loads it when a task matches its description.

How do I install Harness MCP Scan in Codex?

Run `npx skills add ruvnet/ruflo --skill harness-mcp-scan -a codex`. Or copy the skill folder (plugins/ruflo-metaharness/skills/harness-mcp-scan in ruvnet/ruflo) into .agents/skills/harness-mcp-scan in your project. Codex loads it when a task matches its description.

Can I use Harness MCP Scan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill harness-mcp-scan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-mcp-scan, .gemini/skills/harness-mcp-scan, .github/skills/harness-mcp-scan and .opencode/skills/harness-mcp-scan in your project.

What does Harness MCP Scan need to run?

SKILL.md names no scripts, command-line tools or credentials: Harness MCP Scan is instructions for the agent only. Its frontmatter pre-approves these tools: Bash.

Does Harness MCP Scan access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Harness MCP Scan safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Harness MCP Scan use?

Harness MCP Scan is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Harness MCP Scan use?

About 429 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Harness MCP Scan?

Skills that share tags, products or a category with Harness MCP Scan: Security Scan (affaan-m/ECC, 276k stars), Flow Swarm (LeoYeAI/openclaw-master-skills, 2.2k stars), MCP Security Audit (boshi-xixixi/TraeSkill, 276 stars) and Keel (joseconti/declaracion-renta-espana, 190 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Harness MCP Scan?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,222 GitHub stars. The repository holds 265 skills in this directory. The repository was last updated on October 10, 2026.

Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.