Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
agentcontext
MCP serversNormalize AGENTS.md / CLAUDE.md / .cursor/rules / .clinerules / .windsurf/rules from one source.
@mbeato/agentcontext-mcp@0.1.2 -
raportagent-mcp
MCP serversSourced market and compliance research for Claude Desktop, Claude Code and Cursor.
@raportagent/mcp@0.1.2 -
Agent Cowork Memory
MCP serversShared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
agent-cowork-memory@0.3.2 -
speclock
MCP serversAI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
speclock@5.5.3 -
StillOnline
MCP serversStillOnline MCP: uptime, status pages, checks. REST API for Cursor and Claude Code.
stillonline-mcp@0.3.6 -
mcp-server
MCP serversQuery Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.
@spanlens/mcp-server@0.3.0 -
mcp
MCP serversDraft, publish, and manage your VeloCMS blog from Claude, Cursor, or any MCP client.
@velocms/mcp@0.1.3 -
Aalto
MCP serversFF&E product library for interior designers. Connect Claude, ChatGPT and Cursor.
-
GymUp
MCP serversConnect Claude, Cursor or any MCP client to your GymUp training data.
-
Vibesignet
MCP serversWebsite templates with tested build prompts for Claude Code, Codex and Cursor.
-
Awesome-Agent-Harnesses
Agents & frameworksCurated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.
git clone https://github.com/NeuraLiying/Awesome-Agent-Harnesses.git -
nobrainer-tech-flow
SkillsFrom task to done. One open source workflow of 18 modules for AI coding agents that runs the AI-native SDLC: plan, design, build, test, deploy, maintain, with evidence in every handoff. Free, MIT.
git clone https://github.com/nobrainer-tech/nobrainer-tech-flow.git -
codesearch
MCP serversMulti-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.
git clone https://github.com/flupkede/codesearch.git -
ScientificFigureLibrary
MCP serversLocal-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.
git clone https://github.com/xuzhougeng/ScientificFigureLibrary.git -
android-use
MCP serversGive AI agents fast, bounded access to a real Android device or emulator. MCP server and CLI for Claude Code, Codex, Cursor, and more.
git clone https://github.com/austinintelligence/android-use.git -
docling-Studio
AI repositoriesChunkless RAG for AI agents, powered by Docling. Parse your PDFs, inspect every title, table and box on the page, then let any MCP client (Claude, Cursor…) read only the sections it needs under a token budget and cite exact, server-verified passages. No chunks, no embeddings, no vector store.
git clone https://github.com/scub-france/docling-Studio.git -
alloy
MCP serversConnect Claude, Cursor, Codex, and other AI tools to your robotics mission data.
-
seo-audit
MCP serversRun SEO + AI-visibility (GEO) audits from Claude, Cursor & other AI clients.
-
build
MCP serversStart a NorthernGo cloud build from Cursor, Claude or Codex. EU database included.
-
Overskill
MCP serversBuild and publish Overskill apps from Cursor, Claude, ChatGPT, or any MCP client.
-
QuickSnip
MCP serversGive Claude, Cursor, or another AI assistant direct access to your QuickSnip library.
-
mcp
MCP serversWontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.
wontopos-mcp@1.0.29 -
Rules MCP
MCP serversMCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity.
@akr1166org/rules-mcp@0.3.1 -
context-sync
MCP serversUniversal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
@context-sync/server@1.0.1
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.