DecimalAI Skills Registry MCP server
ai.decimal/registry·v0.1.3·1 starsSearch agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.
1 stars
Reviews
Write oneNobody has reviewed DecimalAI Skills Registry yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
DecimalAI Skills Registry tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
get_leaderboardRanked skills leaderboard.
get_skillGet one skill's full record: trust/safety-scan status, verified benchmark evidence (lift vs no-skill baseline), SkillScore, ratings, and the SKILL.md body.
search_skillsSearch the public DecimalAI skills registry.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 18 days ago15/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How DecimalAI Skills Registry compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 4,460 AI and agents servers
- Tools
- 3
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 50% of 2,711 AI and agents servers
What its tools let an agent do: 3 read
Install DecimalAI Skills Registry in Claude Code, Cursor or VS Code
claude mcp add registry -- uvx decimalai-mcp
What the publisher says
From the DecimalAI Skills Registry repository's README, as published. We do not edit it. Read it on GitHub
decimalai-mcp
Part of DecimalAI. Most users want the Python SDK → decimal-labs/decimalai-python.
MCP server for the DecimalAI skills registry — the registry that ranks agent skills by measured effectiveness (verified A/B benchmarks, live pass rates, AI rater scores), not download counts.
<!-- mcp-name: ai.decimal/registry -->
Gives any MCP client (Claude Desktop, Claude Code, Cursor, …) three read-only tools:
No API key required — all three tools read public registry endpoints. If you set DECIMALAPIKEY (from app.decimal.ai/settings), the same tools additionally show which skills your org has already installed (installed_as).
Install
pip install decimalai-mcp
# or, no install needed at config time:
uvx decimalai-mcpRequires Python 3.10+.
Claude Code
claude mcp add decimalai -- uvx decimalai-mcp
# with an API key:
claude mcp add decimalai -e DECIMAL_API_KEY=dai_sk_... -- uvx decimalai-mcpClaude Desktop
Add to claudedesktopconfig.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"decimalai": {
"command": "uvx",
"args": ["decimalai-mcp"],
"env": {
"DECIMAL_API_KEY": "dai_sk_optional"
}
}
}
}Omit the env block entirely for anonymous read-only access.
Configuration
Why no checkmanifestimpact tool?
The manifest-impact endpoint (POST /api/v1/regression-check) is authenticated on the platform — it analyzes your org's production traces against a candidate manifest, so there is no public variant to expose. This server is deliberately a read-only, key-optional public-registry surface. If demand shows up, an authed checkmanifestimpact (requiring DECIMALAPIKEY) is a natural v0.2 addition; the regression-check GitHub Action covers the CI use-case today.
Endpoints used (all public)
- GET /api/v1/registry/skills — browse/search
- GET /api/v1/registry/skills/{slug} — detail
- GET /api/v1/registry/leaderboard — ranked leaderboard (category filtering falls back to the browse endpoint's documented view=ranks mode, because the leaderboard endpoint is uncategorized)
Development
pip install -e ".[dev]"
pytest # all HTTP mocked; no network
python -m decimalai_mcp.server # run over stdioRun pytest yourself before opening a PR. CI also asserts that the pinned mcp<2 still provides FastMCP, which the mocked tests do not cover — run that one too:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
DecimalAI Skills Registry: common questions
- Is DecimalAI Skills Registry MCP server safe?
- Mostly: it is graded B (80/100). Read the DecimalAI Skills Registry safety report
- How do I install DecimalAI Skills Registry?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does DecimalAI Skills Registry need an API key?
- Yes. The registry entry asks for
DECIMAL_API_KEY. - Is DecimalAI Skills Registry maintained?
- The last commit was 20 days ago (2026-10-15). The latest release is v0.1.3.
- What can I use instead of DecimalAI Skills Registry?
- Servers from other publishers that do the same job: mcptoon MCP server, Pm Claude Skills MCP server and Watch Skill MCP server.
- How does DecimalAI Skills Registry compare with other AI and agents MCP servers?
- safety score 80/100 (higher than 60% of 4,460 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to DecimalAI Skills Registry
Same job from other publishers: the closest match first, then the best rated.
- mcptoonMCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).not reviewedEstablishedA
- Pm Claude Skills1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.not reviewedEstablishedA
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- three.ws MarketplaceBrowse and discover the public three.ws agent marketplace and skills catalog. Read-only.not reviewedEstablishedA
- Vibe CheckMetacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safetynot reviewedEstablishedB