pypi decimalai-mcpstdioMITupdated 19d ago
Part of DecimalAI. Most users want the Python SDK → decimal-labs/decimalai-python.
What can you do with DecimalAI Skills Registry?
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.
Gives any MCP client (Claude Desktop, Claude Code, Cursor, …) three read-only tools:
| Tool | What 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 |
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
pip install decimalai-mcp
# or, no install needed at config time:
uvx decimalai-mcp
Requires 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-mcp
Claude Desktop
Add to claude_desktop_config.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
| Env var | Default | Purpose |
|---|---|---|
DECIMAL_API_KEY |
(unset) | Optional. Unlocks per-org enrichment (e.g. installed_as) on the same public endpoints. |
DECIMAL_API_URL |
https://api.decimal.ai |
Point 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/searchGET /api/v1/registry/skills/{slug}— detailGET /api/v1/registry/leaderboard— ranked leaderboard (categoryfiltering falls back to the browse endpoint's documentedview=ranksmode, because the leaderboard endpoint is uncategorized)
Development
pip install -e ".[dev]"
pytest # all HTTP mocked; no network
python -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:
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
Install
Add DecimalAI Skills Registry to your client. Pick the one you use.
claude mcp add decimalai-mcp -- uvx decimalai-mcpcodex mcp add decimalai-mcp -- uvx decimalai-mcpamp mcp add decimalai-mcp -- uvx decimalai-mcp{
"mcpServers": {
"decimalai-mcp": {
"command": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"decimalai-mcp": {
"command": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
code --add-mcp '{"name":"decimalai-mcp","command":"uvx","args":["decimalai-mcp"]}'Or add the block manually to `.vscode/mcp.json` under `servers`.
{
"mcpServers": {
"decimalai-mcp": {
"command": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"decimalai-mcp": {
"command": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"decimalai-mcp": {
"command": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"decimalai-mcp": {
"type": "local",
"command": "uvx",
"args": [
"decimalai-mcp"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"decimalai-mcp": {
"command": {
"path": "uvx",
"args": [
"decimalai-mcp"
]
}
}
}
}Add to your Zed `settings.json`.
uvx decimalai-mcpRun `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
Score
39 / 100
Incomplete
- Documentation25/25
- Maintenance19/25
- Trust16/20
- Capability0/15
- Install experience12/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 12 days ago
- Has a release history
- Repository is not archived
- Licensed MIT
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 0 tool(s) documented
- Provides prompt templates
- Provides resources
- 12 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
Version history
| Versions | Published |
|---|---|
| 0.1.3Latest | Aug 20, 2026 |