DecimalAI Skills Registry

ai.decimalPublished by decimal.aiv0.1.3Updated Oct 24, 2026

Search agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper ToolsAI & ML

Overview

AI-generated overview

Read-only search and leaderboard tools for the DecimalAI public skills registry, ranking agent skills by measured benchmark effectiveness.

What you can do
Exposes three read-only tools over the public DecimalAI skills registry: search_skills for hybrid keyword and semantic search, get_skill for a full record including safety-scan status, verified benchmark lift, SkillScore, ratings and the SKILL.md body, and get_leaderboard for ranked lists by skill_score, biggest_improvement, efficiency or top_rated. All three read public endpoints and work anonymously. Setting an API key only adds per-organization enrichment such as installed_as.
When to use it
Useful when an assistant needs to find, compare or cite agent skills by measured effectiveness rather than download counts, for example to pick a skill for a task or to check a skill's safety-scan status and benchmark lift before adopting it.
Requirements
Runs locally over stdio as the PyPI package decimalai-mcp, requiring Python 3.10+ (pip install or uvx). Network access to the public registry endpoints is needed. No account or API key is required; the optional secret DECIMAL_API_KEY enables per-org enrichment, and DECIMAL_API_URL can point at a self-hosted backend.
Before you install
The server is read-only and needs no key, so anonymous use sends only search queries to the public registry. If you set DECIMAL_API_KEY, that credential is passed to the server and ties requests to your organization; treat it as a secret and omit it when per-org enrichment is not needed.

Installation

In SourceWeft

  1. Open DecimalAI Skills Registry in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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.

[PyPI] [Downloads] [CI] [Python] [License]

Gives any MCP client (Claude Desktop, Claude Code, Cursor, …) three read-only tools:

ToolWhat it does
search_skills(query, category?, sort?, limit?)Hybrid keyword/semantic search over the public registry
get_skill(slug)Full record: trust & safety-scan status, verified benchmark lift, SkillScore, ratings, SKILL.md body, and how to install it (decimalai skills add <slug>, the folder it lands in, and the Claude Code --plugin-dir line)
get_leaderboard(sort?, category?, window_days?, limit?)Ranked leaderboard: skill_score, biggest_improvement, efficiency, top_rated

No API key required — all three tools read public registry endpoints. If you set DECIMAL_API_KEY (from app.decimal.ai/settings), the same tools additionally show which skills your org has already installed (installed_as).

Install

bash
pip install decimalai-mcp# or, no install needed at config time:uvx decimalai-mcp

Requires Python 3.10+.

Claude Code

bash
claude mcp add decimalai -- uvx decimalai-mcp# with an API key:claude mcp add decimalai -e DECIMAL_API_KEY=dai_sk_... -- uvx decimalai-mcp

Claude Desktop

Add to claude_desktop_config.json (Settings → Developer → Edit Config):

json
{  "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

Env varDefaultPurpose
DECIMAL_API_KEY(unset)Optional. Unlocks per-org enrichment (e.g. installed_as) on the same public endpoints.
DECIMAL_API_URLhttps://api.decimal.aiPoint at a self-hosted / local backend.

Why no check_manifest_impact 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 check_manifest_impact (requiring DECIMAL_API_KEY) 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

bash
pip install -e ".[dev]"pytest              # all HTTP mocked; no networkpython -m decimalai_mcp.server   # run over stdio

Run 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:

bash
python -c "from mcp.server.fastmcp import FastMCP; import decimalai_mcp.server"

Releases are cut from a published GitHub Release — see RELEASING.md for the gates a change has to pass and the version strings that must move together.

License

MIT

Source: README.md at commit a033c9f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts