agentmods.dev

mcp

mcp is a command for Claude Code from nguyenthienthanh/aura-frog. It costs 0 tokens per session (1,166 once invoked), scanned A, original, MIT.

A set of commands for checking and managing Model Context Protocol (MCP) connections. MCP is a way for an AI agent to access external tools or services.

In plain words
What is it for?
Use it to view server status, audit recent calls, filter blocked calls, reset session or server limits, and test one server’s connectivity.
Why use it?
It makes enabled servers, usage limits, blocked calls, and sanitized activity logs visible, and provides controlled ways to test connections or reset counters.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aura-frog plugin — 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

not rated 24 yesterday A scan 0 tokens original MIT
View the source file nguyenthienthanh/aura-frog ethannguyenlabs.xyz
Install

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.

agentmods
npx agentmods add commands/nguyenthienthanh/aura-frog/mcp
Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

Made for: Claude Code.

Or install aura-frog, the plugin that ships this one along with the rest of its 43 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

Wrote 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.

agentmods badge for mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/mcp.svg)](https://agentmods.dev/commands/nguyenthienthanh/aura-frog/mcp)
Your own site
<a href="https://agentmods.dev/commands/nguyenthienthanh/aura-frog/mcp"><img src="https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,166 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01166
Opus 5 $0.00000 $0.00583
Sonnet 5 $0.00000 $0.00233
Haiku 4.5 $0.00000 $0.00117

Measured 6d ago against content hash f57d19238558, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp scanned grade A with 0 findings 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 6d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

aura-frog/commands/mcp.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aura-frog:mcp

MCP security operations. Status, audit, rate-limit reset, connectivity test.

Usage

/aura-frog:mcp status                  # which servers enabled, agent allowlists, current usage vs limits
/aura-frog:mcp audit [--window 24h]    # show audit log (sanitized) — calls, blocks, rate-limit hits
/aura-frog:mcp audit --blocked-only    # only blocked calls (forensics view)
/aura-frog:mcp reset-limits [--mcp X]  # reset session counters (logged event); without --mcp resets all
/aura-frog:mcp test <server>           # single-call connectivity test (e.g., context7 ping)

Protocol — status

mcp_status{servers_enabled,total_audited_today,blocked_today,sessions_limited}:
  6,142,3,1

per_server[6]{server,enabled,calls_today,used_pct,rate_limit}:
  context7,true,87,29% of 200,30/min · 200/session
  playwright,true,12,—,30/min · 200/session
  vitest,true,18,—,30/min · 200/session
  firebase,true,5,—,30/min · 200/session
  figma,true,8,—,30/min · 200/session
  slack,true,4,—,30/min · 200/session

per_agent_allowlists[*]{agent,allowlist}:
  ...

Protocol — audit

  1. Read <security-dir>/mcp-audit.jsonl (already sanitized — no credentials in this file). <security-dir> resolves as $AF_SECURITY_DIR, else .claude/security/ if it exists, else .aura/security/ — see hooks/lib/security-dir.cjs.
  2. Project via mcp-security-auditor skill (NEVER load raw JSONL into context)
  3. Filter by --window (default 24h) and --blocked-only if set
  4. Render TOON summary + top 10 events
audit_summary{window,total,success,blocked,rate_limit_hits,top_agent,top_mcp}:
  24h,142,139,3,2,architect,context7

blocked[3]{ts,agent,mcp,reason}:
  2026-05-07T10:30,backend,postgres,destructive_op_blocked
  2026-05-07T11:45,frontend,figma,allowlist_violation
  2026-05-07T12:10,architect,redis,destructive_op_blocked

Protocol — reset-limits

  1. Read .claude/logs/.mcp-rate-counter.json
  2. Reset specified counters (or all if --mcp not given)
  3. Append history.jsonl: event: mcp_limits_reset, mcp: <server> (or all), actor: user
  4. Render confirmation

Read the full file on GitHub · 94 lines

Changes

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.

  1. 6d ago First seen · 94 lines · 0 tokens per session scan A f57d19238558

Subscribe to this mod's changes

mcp is a command published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,166 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Securityai-assisted-developmentai-for-developersclaude-codecode-qualitycontext-engineeringdeveloper-productivity
Related

Other commands, from other repositories

review-agentready

AgentReady-specific code review with attribute mapping and score impact analysis.

ambient-code/agentready · 12 tokens

review-pr

Multi-agent PR review with four modes (review, re-review, self-review, address-feedback) - spawns parallel subagents, saves diff to /tmp for context efficiency, supports file exclusion patterns.

hoblin/claude-ruby-marketplace · 39 tokens

resume_handoff

Resume work from handoff document with context analysis and validation.

hoblin/claude-ruby-marketplace · 11 tokens

feature

Command "feature" from hoblin/claude-ruby-marketplace, covering input format, context, workflow, step 1: setup and step 2: gather historical context.

hoblin/claude-ruby-marketplace · 0 tokens

speckit.specify

Create or update the feature specification from a natural language feature description.

ambient-code/agentready · 13 tokens

speckit.checklist

Generate a custom checklist for the current feature based on user requirements.

ambient-code/agentready · 13 tokens