No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by sidequery · MCP Server · ★ 122
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sidemantic safe to install? View the security audit →
Sidemantic The universal metrics layer for consistent metrics across your data stack. Compatible with 15+ semantic model formats. Supported Formats: Sidemantic (YAML, Python or SQL), Power BI TMDL, Cube, dbt MetricFlow, LookML, Hex, Rill, Superset, Omni, BSL, GoodData LDM, Snowflake Cortex, Malloy, OSI, AtScale SML, ThoughtSpot TML Databases: DuckDB, MotherDuck, PostgreSQL, BigQuery, Snowflake, ClickHouse, Databricks, Spark SQL (also via ADBC) Documentation Demo (50+ MB data download, runs in your browser with Pyodide + DuckDB) The installer downloads the skill to and symlinks it into . Quickstart Install: Malloy support (uv): DAX and Power BI TMDL support (uv): HTTP API server (uv): Notebook widget (uv): Marimo (uv): python import duckdb from sidemantic.widget import MetricsExplorer conn = duckdb.connect(":memory:") conn.execute("create
| Stars | 122 |
| Forks | 12 |
| Language | Python |
| Category | MCP Server |
| License | AGPL-3.0 |
| Quality Score | 62.540667835746/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-22 |
| Created | 2025-10-04 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with sidemantic for enhanced workflows:
Looking for a sidemantic alternative? If you're comparing sidemantic with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Source-available semantic layer and sidecar for agentic AI and governed analytics. Compiles declarative YAML m
Open-source Semantic Sidecar for AI, analytics, and governed data systems. Compiles declarative YAML models in
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent
Databao Context Engine is an open-source engine that automatically generates a governed semantic context from
An MCP server to query any Postgres database in natural language.
Demo of a customer service agent (Cymbal Air) using LangGraph, Tools, and RAG to interact with Google Cloud Da
Explore other popular mcp server tools:
sidemantic is The universal metrics layer. Compatible with 15+ formats: Cube, MetricFlow, LookML, Omni, BSL, LDM, Cortex, Malloy, OSI, SML, TML, Hex, Rill, Superset. It is categorized as a MCP Server with 122 GitHub stars.
sidemantic is primarily written in Python. It covers topics such as ai, analytics, analytics-engineering.
You can find installation instructions and usage details in the sidemantic GitHub repository at github.com/sidequery/sidemantic. The project has 122 stars and 12 forks, indicating an active community.
sidemantic is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to sidemantic on Agent Skills Hub include orionbelt-semantic-layer, orionbelt-semantic-layer, ktx-ai-data-agents-mcp-context-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: