Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
validatehtml
MCP serversValidate HTML, CSS, JSON, XML and WCAG accessibility from an AI coding agent. No key needed.
validatehtml@0.1.0 -
devpulse
MCP serversTells your AI coding assistant what's wrong with your local dev environment in one call.
devpulse-mcp@0.1.3 -
verifAIed
MCP serversVerify what your AI coding agent built: test coverage, recorded browser tests, a done verdict.
-
prompt-warrior
SkillsAgent skill: your AI coding logs as a gamified character sheet — Claude Code, Codex, OpenCode, Gemini, Copilot. 74 achievements, fixed-scale metrics, LLM-written chronicle, research-backed advice. 100% local, RU/EN.
git clone https://github.com/timoncool/prompt-warrior.git -
delegate-router
SkillsClaude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.
git clone https://github.com/pvjbuilds/delegate-router.git -
apple-design-skill
Skills🍎 Apple HIG & Apple Design System skill for all AI coding agents (Claude Code, Cursor, Copilot, Antigravity, Windsurf)
git clone https://github.com/XOVIET-GAME/apple-design-skill.git -
map-animation-skills
SkillsAnimated map skills for AI coding agents — draw routes, zoom-to-location, and data-driven map animations rendered to video.
git clone https://github.com/iart-ai/map-animation-skills.git -
neat
MCP serversLive code graph that fuses static analysis (tree-sitter) with OpenTelemetry runtime traces, queried over MCP so AI coding agents get real full-stack context.
git clone https://github.com/neat-technologies/neat.git -
Yokka
MCP serversKanban board for AI coding agents: they claim cards, report progress, ask you when blocked, ship.
-
Entalpa Requirements MCP
MCP serversSpec-driven development for AI coding agents: live requirements, stories and traceability over MCP
-
OverlayQA
MCP serversRun accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
@overlayqa/mcp@0.8.0 -
cubic
MCP serversTriage cubic AI code review findings, start PR reviews, and read wikis, scans, and team learnings.
-
Reality Graph Verification Tools
MCP serversRead-only AI coding tools for change verification, release readiness, capacity, and guidance.
-
StateLode
MCP serversShared task layer for AI coding agents. One MCP surface: task_search, task_get, task_mutate.
statelode-bridge@0.1.9 -
Stele
MCP serversShared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
-
Nofax
MCP serversHuman-in-the-loop approvals and notifications for AI coding agents through a local stdio MCP server.
nofax@0.2.50 -
TokenSaver
MCP serversStructural warm start for AI coding agents in .NET: cheap Roslyn signature maps of C#/.NET files.
TokenSaver.Mcp@1.15.5 -
codeweb
MCP serversSee what your AI edits affect. Structural checks for AI code changes. 28 MCP tools, no LLM.
@ghostlygawd/codeweb@0.15.0 -
Credence — Epistemic Guard
MCP serversEpistemic guard for AI coding: tracks uncertain values and blocks writes until verified.
credence-guard@1.2.5 -
projectmind
MCP serversPersistent project memory for AI coding agents: one compact digest instead of re-reading the repo.
@nodemint/projectmind@0.6.0 -
Sprintra
MCP serversThe project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
@sprintra/mcp@1.0.3 -
Agent Readiness
MCP serversDeterministic, read-only audits of repo readiness for AI coding agents and of agent context files.
@alipajand/agent-readiness-mcp@0.1.2 -
BetaDrop
MCP serversPublish iOS and Android builds to testers and manage share links from an AI coding agent.
@betadrop/mcp@0.2.5 -
Octocode MCP - AI Context Platform
MCP serversAI code research platform. Search, analyze, and extract insights from any GitHub repository.
octocode-mcp@7.0.9
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.