Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Bigsy/mcpmu --skill skill_datagit clone --depth 1 https://github.com/Bigsy/mcpmuWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bigsy/mcpmu/skill_data)<a href="https://agentmods.dev/skills/bigsy/mcpmu/skill_data"><img src="https://agentmods.dev/badge/skills/bigsy/mcpmu/skill_data/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bigsy/mcpmu/skill_data"><img src="https://agentmods.dev/badge/skills/bigsy/mcpmu/skill_data.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 4 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium Excessive Agency · line 215 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 142 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 161 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 143 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 162 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.06036 |
| Opus 5.5 | $0.00032 | $0.02414 |
| Sonnet 5.5 | $0.00016 | $0.01207 |
| Haiku 4.5 | $0.00008 | $0.00604 |
Grade A, and why
mcpmu scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(mcpmu *), Bash(brew *), Bash(go install *), Bash(claude mcp *), Bash(codex mcp *), Bash(which mcpmu), Bash(command -v mcpmu), Bash(curl http://127.0.0.1:*), Bash(curl http://localhost:*) How it starts
The opening of the file, as written. The whole thing — 584 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpmu — MCP Server Manager
mcpmu is a multiplexing MCP server manager. You configure MCP servers once in mcpmu, then expose them as a single unified MCP endpoint to any agent (Claude Code, Codex, Cursor, Windsurf, etc.).
Installing mcpmu
First check if mcpmu is already installed:
which mcpmu
If not installed, install via Homebrew (preferred) or Go:
Homebrew (macOS/Linux):
brew tap Bigsy/tap && brew install mcpmu
From source (requires Go):
go install github.com/Bigsy/mcpmu/cmd/mcpmu@latest
Installing / updating this skill
The skill ships inside the mcpmu binary. Re-run install after upgrading mcpmu to pick up the latest version:
mcpmu skill install # ~/.agents/skills/mcpmu/ plus detected agents (~/.claude/skills, ~/.codex/skills)
mcpmu skill uninstall # remove it from everywhere
Registering mcpmu as an MCP Server
After installing mcpmu, register it so your agent can use all mcpmu-managed servers through a single endpoint.
Claude Code:
claude mcp add mcpmu -- mcpmu serve --stdio
Codex:
codex mcp add mcpmu -- mcpmu serve --stdio
OpenCode (global config ~/.config/opencode/config.json, or project-level opencode.json):
{
"mcp": {
"mcpmu": {
"type": "local",
"command": ["mcpmu", "serve", "--stdio"]
}
}
}
Any MCP config JSON (Cursor, Windsurf, etc.):
{
"mcpmu": {
"command": "mcpmu",
"args": ["serve", "--stdio"]
}
}
With a specific namespace:
claude mcp add work -- mcpmu serve --stdio --namespace work
codex mcp add work -- mcpmu serve --stdio --namespace work
OpenCode (namespace-specific):
{
"mcp": {
"work": {
"type": "local",
"command": ["mcpmu", "serve", "--stdio", "--namespace", "work"]
}
}
}
With management tools (lets the agent inspect and start/stop servers via MCP):
claude mcp add mcpmu -- mcpmu serve --stdio --expose-manager-tools
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +88 lines · +17 tokens per session c3e8b90635b5
- 1mo ago Changed · +1 lines 22004817862e
- 1mo ago Changed · +18 lines 14fa46df45e7
- 2mo ago First seen · 477 lines · 64 tokens per session scan A c3a9e147b871
mcpmu is a skill published in the GitHub repository Bigsy/mcpmu (19 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 6,036 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
collection
Choose which SkillNote skill collection is active for this Codex project. Use when the user says "change collection", "switch skills", "use frontend skills", or "show collections".
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
cmux
End-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash). Use when automation needs deterministic placement and navigation in a multi-pane cmux layout.