mcp commands

1,257 tagged mcp, measured the same way as everything else here.

Browse within: mcp-server 292model-context-protocol 267LLM 168claude-code-plugin 167cli 154ai-tools 138cursor 133skills 82open-source 80agents 79knowledge-graph 70agent-memory 50ai-assistant 50agent 49

docs

01

upstash/context7

Command Claude Code

Look up documentation for any library.

not rated 63k +261 changed 3d ago A 6 tokens original MIT

CHANGELOG

02

bytedance/UI-TARS-desktop

Command Claude Code ✓ vendor

Command "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25.

not rated 39k +61 8d ago A 0 tokens original Apache-2.0

skillspector

03

NVIDIA/SkillSpector

Command Claude CodeOpenCode ✓ vendor

Scan an AI agent skill for security risks with SkillSpector (static analysis by default); use when vetting a skill before install or auditing one in use.

not rated 20k +509 today A 32 tokens original Apache-2.0

minutes-brief

04

silverstein/minutes

Command Claude CodeOpenCode

Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who…

not rated 1.6k +11 today A 146 tokens original MIT

recall

05

vshulcz/deja-vu

Command Claude Code

Search this machine's past AI coding sessions (deja-vu).

not rated 1.2k +50 changed yesterday A 17 tokens copy · 97% MIT

commit

06

dtsola/xiaoyaosearch

Command Claude Code

This command helps you create well-formatted commits with conventional commit messages and emoji.

not rated 1.0k +2 14d ago A 0 tokens

hunt

07

H-mmer/pentest-agents

Command Gemini CLI

Active vulnerability hunting on a target. Loads scope, reads brain, detects tech stack, runs targeted tests with concrete payloads. Usage: /hunt target.com [--vuln-class idor|xss|ssrf|sqli|ssti|oauth|rce|race|graphql|upload|business-logic|llm-ai].

not rated 1.0k +17 4mo ago A ✓ AI review 0 tokens

save-memory

09

0xK3vin/MegaMemory

Command Claude Code

You are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared.

not rated 725 +6 5mo ago A 0 tokens original MIT

commit

10

BigSweetPotatoStudio/HyperChat

Command Claude Code

A command for submitting a change, with an optional argument supplied through $ARG.

not rated 709 1mo ago A 0 tokens

trellis-finish-work

11

fy-agent/fyagent

Command Claude CodeCursor needs its repo

Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.

not rated 831 +1.4k today A 0 tokens

code-review

12

truffle-ai/dexto

Command Claude Code

Review code for bugs, improvements, and best practices with actionable feedback.

not rated 652 +2 today A 16 tokens

package

13

VikashLoomba/copilot-mcp

Command Claude Code

Look up library documentation using Context7 MCP tools for a specific task.

not rated 505 +1 4mo ago A 13 tokens GPL-3.0

update-faq

15

Arenukvern/mcp_flutter

Command Claude CodeCursor

could you please update DESIGNFAQ & DXFAQ based on the changes we are trying to achieve.

not rated 389 +3 5d ago A 0 tokens original MIT

flaremo-setup

16

realchendahuang/FlareMo

Command Claude Code

A one-time setup command for connecting the FlareMo memory ledger. It checks the service address, access token, connection, authentication, and placement of the related skill.

not rated 312 +7 changed 22d ago A 43 tokens AGPL-3.0

validate

17

dylanroscover/Embody

Command Claude Code

Pre-handoff validation checklist. Run this before declaring a task complete.

not rated 202 +2 yesterday A 0 tokens original MIT

debug

18

echoVic/blade-code

Command Claude Code

A command for investigating software errors by classifying them, tracing their source, and comparing expected with actual behaviour.

not rated 180 3d ago A 5 tokens original MIT

stop

19

mtarcure/claude-vibe-squad

Command Claude Code

Gracefully close the Vibe Squad tmux session from inside Chrono.

not rated 165 26d ago A 0 tokens original MIT

fix

20

Goldziher/ai-rulez

Command Claude Code

Auto-fix linting, formatting, and common issues.

not rated 163 +2 changed 6d ago A 11 tokens original MIT

mpm-init

21

bobmatnyc/claude-mpm

Command Claude Code

Initialize or update project for Claude Code and MPM.

not rated 157 +1 1mo ago A 10 tokens

plan

22

dmae97/omk

Command Claude Code

Generate specs/[###-feature]/plan.md from the active feature specification.

not rated 148 +3 today A 0 tokens

resume-workflow

23

moira-mcp/moira

Command Claude Code

Resume workflow execution from current branch context.

not rated 127 +12 yesterday A 7 tokens original Apache-2.0

adversarial-review

24

AgentToolkit/altk-evolve

Command Claude Code

Adversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review).

not rated 124 +1 today A 26 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: