Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Toon Memory
MCP serversOffline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
toon-memory@4.3.5 -
datahub-countries-mcp
MCP serversCountry codes, names, and regions from the DataHub country catalog. No key required.
datahub-countries-mcp@1.0.1 -
Zippopotam
MCP serversZippopotam MCP — wraps Zippopotam.us ZIP/postal code API (free, no auth)
@pipeworx/mcp-zippopotam@1.1.1 -
executing-plans
SkillsUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
-
Kwipu
AI repositoriesAsk questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
git clone https://github.com/benmaster82/Kwipu.git -
hive-mind
MCP serversShared memory for your AI agents: a fact one agent writes on one machine is there for the next agent and the next machine, with no server in between. AGPL-3.0, alpha.
git clone https://github.com/projectmentor/hive-mind.git -
Antideploy
MCP serversDeploy and run apps from your coding agent. Sign in with one link; no dashboard or Dockerfile.
antideploy-mcp@0.2.0 -
Linkbreakers Docs
MCP serversSearch and read Linkbreakers docs, pricing and QR code templates. Read-only, no auth.
-
MarketCheck API Docs
MCP serversMarketCheck API docs for coding assistants: search, endpoint reference, plans. Free, no auth.
-
QuintaDB
MCP serversNo-code databases, forms, portals and AI sites. Manage records and automation via natural language.
-
adrkit decision memory
MCP serversDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
@adrkit/mcp@0.20.0 -
mess
MCP serversInventory of your service accounts, kept current by your coding agents. Metadata only, no secrets.
-
Dunstan
MCP serversChecks a coding agent's handback against the pull request's GitHub record. No model decides.
dunstan@0.1.23 -
toolweave
MCP serversOne MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
-
Memory Fabric
MCP serversFile-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
memory-fabric@1.4.5 -
LoreConvo
MCP serversLocal-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.
loreconvo@0.11.0 -
claude-bridge-mcp
MCP serversPipes Claude Code session output into Claude Chat — no more copy-paste between tools
@rahulonramp2807/claude-bridge-mcp@2.2.0 -
agent-claim-mcp
MCP serversFile-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
@vk0/agent-claim-mcp@1.0.2 -
QuintaDB
MCP serversNo-code databases, forms, portals and AI sites. Manage records and automation via natural language.
-
validatehtml
MCP serversValidate HTML, CSS, JSON, XML and WCAG accessibility from an AI coding agent. No key needed.
validatehtml@0.1.0 -
rapidbm25
MCP serversFast local BM25 keyword search over texts or a code/docs folder. Rust core, no network.
rapidbm25@0.2.0 -
agentic-qa-boilerplate
SkillsAgentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.
git clone https://github.com/upex-galaxy/agentic-qa-boilerplate.git -
drawing-skill
SkillsClaude draws by hand, one mark at a time, on a real tldraw canvas: measuring, blocking in, colour, ink, with each stage checked. No image model.
git clone https://github.com/jchapuis/drawing-skill.git -
Coupondroid Chile
MCP serversLive coupons, promo codes and deals from online shops in Chile. Read-only, no login.
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.