LoopSkill MCP server
online · 100% uptimeio.github.wisechef-ai/loopskill·v0.9.65·2 starsSearch, install and compose AI agent skills, loops and bundles from the LoopSkill marketplace.
2 stars
Reviews
Write oneNobody has reviewed LoopSkill yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
LoopSkill tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 529ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityauth enforced (unknown)9/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How LoopSkill compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 85/100
- higher than 73% of 4,460 AI and agents servers
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 429 ms
- faster than 32% of 2,331 AI and agents servers
- GitHub stars
- 2
- more than 65% of 2,711 AI and agents servers
Install LoopSkill in Claude Code, Cursor or VS Code
claude mcp add --transport http loopskill https://app.loopskill.io/api/mcp/http/
What the publisher says
From the LoopSkill repository's README, as published. We do not edit it. Read it on GitHub
LoopSkill
A local CLI for skills you already have, plus a self-hostable registry to pull more from. Start with the CLI — it needs no account and makes no network call for import/diff.
60 seconds: see skill drift, reproducibly
This is a literal, self-contained transcript. Paste every command below into a clean shell — it fabricates two fake "skill" installs, edits one and deletes the other to simulate drift, then diffs. You will get exactly this output; nothing here depends on skills you already have installed.
git clone https://github.com/wisechef-ai/loopskill-api && cd loopskill-api
python3 -m venv .venv && ./.venv/bin/pip install ./cli
alias loopskill=./.venv/bin/loopskill # or add ./.venv/bin to PATH
loopskill --version
# --- fabricate a "machine" with two skills, take a snapshot ---
mkdir -p /tmp/loopskill-demo/home/.claude/skills/agent-reach
mkdir -p /tmp/loopskill-demo/home/.claude/skills/recipes
cat > /tmp/loopskill-demo/home/.claude/skills/agent-reach/SKILL.md <<'EOF'
---
name: agent-reach
description: Give your agent eyes on the internet.
---
Body v1.
EOF
cat > /tmp/loopskill-demo/home/.claude/skills/recipes/SKILL.md <<'EOF'
---
name: recipes
description: Recipe search skill.
---
Body.
EOF
loopskill import --home /tmp/loopskill-demo/home -o /tmp/loopskill-demo/machine-a.lock.json
# --- simulate drift: edit one skill, delete the other ---
cat > /tmp/loopskill-demo/home/.claude/skills/agent-reach/SKILL.md <<'EOF'
---
name: agent-reach
description: Give your agent eyes on the internet.
---
Body v2 — updated tool list.
EOF
rm -rf /tmp/loopskill-demo/home/.claude/skills/recipes
loopskill diff /tmp/loopskill-demo/machine-a.lock.json - --home /tmp/loopskill-demo/homeloopskill 0.3.0
loopskill import: wrote /tmp/loopskill-demo/machine-a.lock.json (2 skill(s) across 1 client(s))
loopskill diff: /tmp/loopskill-demo/machine-a.lock.json vs <live scan>
[claude] DRIFT DETECTED
- only in /tmp/loopskill-demo/machine-a.lock.json: recipes
~ changed: agent-reach
[codex] in sync (0 skill(s))
[cursor] in sync (0 skill(s))
[hermes] in sync (0 skill(s))
DRIFT FOUNDExit code is 1 — drift found, script- and CI-friendly. Run loopskill diff again with nothing changed and exit code is 0. That's the whole pitch: two snapshots, one command, drift visible in the time it took to read this paragraph — on the skills you actually have, not a demo, once you drop --home.
import and diff make zero network calls — this isn't a promise in a docstring, it's a structural guarantee: the network-capable code lives in exactly one module (loopskill.pull) that import/diff never import, and cli/tests/testloopskillcli.py::testimportanddiffmakezeronetwork_calls proves it by breaking socket.socket for the duration of those commands.
Full CLI reference, lockfile format, and pull/apply (the two commands that DO touch the network, opt-in): cli/README.md.
What this repo actually is
Two things, and the CLI is the one to start with:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
LoopSkill: common questions
- Is LoopSkill MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the LoopSkill safety report
- How do I install LoopSkill?
- It runs remotely at app.loopskill.io. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does LoopSkill need an API key?
- Yes. The registry entry asks for
x-api-key. - Is LoopSkill maintained?
- The last commit was 22 days ago (2026-10-13). The latest release is v0.9.65.
- Is LoopSkill up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of LoopSkill?
- Servers from other publishers that do the same job: three.ws Marketplace MCP server, Pm Claude Skills MCP server and Agent-Native Chat MCP server.
- How does LoopSkill compare with other AI and agents MCP servers?
- safety score 85/100 (higher than 73% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 429 ms (faster than 32% of 2,331 AI and agents servers). Full comparison.
Alternatives to LoopSkill
Same job from other publishers: the closest match first, then the best rated.
- three.ws MarketplaceBrowse and discover the public three.ws agent marketplace and skills catalog. Read-only.not reviewedEstablishedA
- Pm Claude Skills1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- mcptoonMCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).not reviewedEstablishedA