mcp-server-sigma

mcp-server-sigma

Enterprise-grade MCP server for Sigma Computing, providing 155 tools for managing workbooks, data models, members, teams, deployments, webhooks, and multi-tenant operations. Enables AI assistants to interact with Sigma via natural language.

Category
访问服务器

README

🚀 mcp-server-sigma

CI PyPI Python License: MIT Coverage

Supercharge your AI Agents with native Sigma Computing superpowers! ⚡
An enterprise-grade Model Context Protocol (MCP) server with 155 tools covering connections, workbooks, data models, members, teams, deployments, webhooks, multi-tenant operations, and composite workflow recipes straight to your favorite AI assistant.


⚠️ Disclaimers & Safety Warnings

[!IMPORTANT] Community Project Disclaimer
mcp-server-sigma is an independent open-source community project. It is not affiliated with, sponsored by, endorsed by, or supported by Sigma Computing, Inc. "Sigma Computing" is a trademark of Sigma Computing, Inc.

[!WARNING] Credentials & Safety Notice
This server uses API credentials scoped to your Sigma organization. Tools can mutate workbooks, users, teams, and data models.

  • Read-Only Mode: To run safely without mutation risk, set SIGMA_MCP_READONLY=1 (grants 83 read-only tools).
  • Destructive Safety Gates: All single-delete tools require explicit confirm=True. Bulk destructive operations (sigma_bulk_deactivate_members, sigma_bulk_remove_team_members) are disabled by default and require SIGMA_MCP_ALLOW_BULK_DESTRUCTIVE=1.
  • Read SECURITY.md before deploying to production.

💡 Why This Exists

Sigma Computing has a unique architectural asymmetry that shapes how you automate it:

  1. Data Models are 100% Code-Representable: You can programmatically construct data models, define columns, joins, and SQL logic, update JSON specs, and swap warehouse sources via API.
  2. Workbook Layouts are UI-Only: Workbook pages, elements, charts, KPIs, and controls have no direct layout-as-code API.

The canonical path to automated BI dashboards is:
Build the layout once in the Sigma UI, save it as a template, then instantiate and source-swap it programmatically forever after! 🎨 ➡️ 🤖

Our composite recipe tools (like sigma_deploy_template_to_folder and sigma_swap_workbook_sources) automate this exact pattern in a single MCP tool call (returning structured step progress or partial failure details if an intermediate step fails):

graph TD
    UI["Sigma UI"] -->|"1. Build Layout Once & Save"| TPL["Sigma Template"]
    Agent["AI Agent / LLM"] -->|"2. Call sigma_deploy_template_to_folder"| MCP["mcp-server-sigma"]
    MCP -->|"POST /v2/templates/{id}/instantiate"| API1["Instantiate Workbook"]
    MCP -->|"POST /v2/workbooks/{id}/swap_sources"| API2["Swap Warehouse Sources"]
    API2 -->|"Delivered"| Dest["Target Customer Folder"]

📦 Quickstart & Installation

1. Install via pip or uv

pip install mcp-server-sigma
# or with uv
uv pip install mcp-server-sigma

Or run via Docker

docker run --rm -i --env-file .env \
  ghcr.io/christianclaudio/mcp-server-sigma:latest

2. Set Environment Variables

export SIGMA_CLIENT_ID="your-client-id"
export SIGMA_CLIENT_SECRET="your-client-secret"
export SIGMA_API_BASE_URL="https://api.us-a.aws.sigmacomputing.com"

[!TIP] Use the API base URL assigned to your organization's region.

Region Base URL
AWS US East https://api.us-a.aws.sigmacomputing.com
AWS US West https://aws-api.sigmacomputing.com
AWS Canada https://api.ca.aws.sigmacomputing.com
AWS EU https://api.eu.aws.sigmacomputing.com
AWS UK https://api.uk.aws.sigmacomputing.com
AWS Australia https://api.au.aws.sigmacomputing.com
Azure US https://api.us.azure.sigmacomputing.com
Azure EU https://api.eu.azure.sigmacomputing.com
Azure Canada https://api.ca.azure.sigmacomputing.com
Azure UK https://api.uk.azure.sigmacomputing.com
Azure Australia https://api.au.azure.sigmacomputing.com
GCP US https://api.sigmacomputing.com
GCP Saudi Arabia https://api.sa.gcp.sigmacomputing.com

🔌 Integration Guides for AI Assistants & IDEs

mcp-server-sigma works seamlessly with all major AI assistants, IDEs, and CLI tools via standard stdio or streamable-http.

<details open> <summary><b>🧡 Claude Desktop & Claude Code</b></summary>

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "sigma": {
      "command": "sigma-mcp",
      "env": {
        "SIGMA_CLIENT_ID": "your-client-id",
        "SIGMA_CLIENT_SECRET": "your-client-secret",
        "SIGMA_API_BASE_URL": "https://api.us-a.aws.sigmacomputing.com"
      }
    }
  }
}

For Claude Code CLI:

claude mcp add sigma -- sigma-mcp

</details>

<details> <summary><b>♊ Google Antigravity & Gemini CLI</b></summary>

Add to your project's .agents/mcp_config.json (or global ~/.gemini/config/mcp_config.json):

{
  "mcpServers": {
    "sigma": {
      "command": "sigma-mcp",
      "args": [],
      "env": {
        "SIGMA_CLIENT_ID": "your-client-id",
        "SIGMA_CLIENT_SECRET": "your-client-secret",
        "SIGMA_API_BASE_URL": "https://api.us-a.aws.sigmacomputing.com"
      }
    }
  }
}

</details>

<details> <summary><b>🤖 OpenAI Codex & Local HTTP Clients</b></summary>

Run in network transport mode (Streamable HTTP) for local CLI & agent extensions:

# Source environment variables from a protected file or secret manager
source .env

# Launch server on HTTP localhost port 8000 for local clients
sigma-mcp --transport streamable-http --host 127.0.0.1 --port 8000

Point your local Codex / HTTP SSE client to http://127.0.0.1:8000/sse.

Note for hosted ChatGPT Actions or Custom GPTs: Hosted cloud services cannot reach localhost. Place an authenticating HTTPS proxy (e.g., ngrok, Cloudflare Tunnel, or Caddy with TLS and Auth) in front of the server before connecting cloud services. </details>

<details> <summary><b>⚡ VS Code (Cline, Roo Code, GitHub Copilot Agent Mode, Continue)</b></summary>

Cline / Roo Code Settings (cline_mcp_settings.json):

{
  "mcpServers": {
    "sigma": {
      "command": "sigma-mcp",
      "env": {
        "SIGMA_CLIENT_ID": "your-client-id",
        "SIGMA_CLIENT_SECRET": "your-client-secret",
        "SIGMA_API_BASE_URL": "https://api.us-a.aws.sigmacomputing.com"
      }
    }
  }
}

Continue.dev Config (~/.continue/config.yaml):

mcpServers:
  - name: sigma
    command: sigma-mcp
    env:
      SIGMA_CLIENT_ID: "your-client-id"
      SIGMA_CLIENT_SECRET: "your-client-secret"
      SIGMA_API_BASE_URL: "https://api.us-a.aws.sigmacomputing.com"

</details>

<details> <summary><b>🐙 GitHub Copilot CLI & Workspace Agent</b></summary>

Add .github/mcp.json to your repository:

{
  "mcpServers": {
    "sigma": {
      "type": "local",
      "command": "sigma-mcp",
      "env": {
        "SIGMA_CLIENT_ID": "${COPILOT_MCP_SIGMA_CLIENT_ID}",
        "SIGMA_CLIENT_SECRET": "${COPILOT_MCP_SIGMA_CLIENT_SECRET}",
        "SIGMA_API_BASE_URL": "https://api.us-a.aws.sigmacomputing.com",
        "SIGMA_MCP_READONLY": "1"
      },
      "tools": ["sigma_get_workbook", "sigma_list_workbooks", "sigma_get_data_model"]
    }
  }
}

Note for Copilot Cloud Agents: Cloud code-review integrations must be configured through Repository Settings > Copilot > MCP servers instead. </details>

<details> <summary><b>❄️ Cortex Code (Snowflake / Enterprise CLI)</b></summary>

Add directly via the Cortex CLI:

cortex mcp add sigma-tools -- sigma-mcp

</details>


🛡️ Safety & Security Controls

Configure behavior using environment variables:

Variable Default Description
SIGMA_CLIENT_ID Required Your Sigma API client ID.
SIGMA_CLIENT_SECRET Required Your Sigma API client secret.
SIGMA_API_BASE_URL Required Region-specific Sigma API host URL.
SIGMA_MCP_PROFILE full Tool registration subset: core (36 tools), admin (52), embed (55), full (155).
SIGMA_MCP_READONLY 0 Set 1 to register only read-only tools (83 tools). Models cannot alter org state.
SIGMA_MCP_ALLOW_BULK_DESTRUCTIVE 0 Set 1 to enable bulk deactivate/remove operations (sigma_bulk_deactivate_members, sigma_bulk_remove_team_members) (157 total).
SIGMA_ALLOWED_TENANTS "" Comma-separated allowlist of tenant org IDs permitted for RFC 8693 token exchange.
SIGMA_STRICT_TENANT_ALLOWLIST 0 Set 1 to fail closed (HTTP 403) if a tenant request is made without an explicit allowlist entry.
SIGMA_MCP_LOG_FORMAT text Set json for structured JSON logging with duration metrics (duration_ms).

📊 Feature & Tool Summary

The server registers 155 tools by default across the following domain modules:

Domain Tools Key Capabilities
Workbooks 33 CRUD, pages, elements, columns, queries, sources, swap, lineage, exports, materializations, bookmarks, tags, grants, embeds
Reports 13 CRUD, elements, queries, lineage, exports, schedules, sources, duplication
Data Models 10 CRUD, JSON spec inspection & editing, elements, columns, sources, swap, lineage, tags
Members 10 List, get, create, update, deactivate, teams, bulk deactivate, email change, onboarding
Teams 10 List, get, create, delete, members, bulk assign/remove, user attributes
Connections 7 List, get, schema sync, connectivity test, columns, grants
Multi-Tenant 6 List tenants, tenant info, capabilities, cross-tenant connection sync
Deployments 6 List, get, create, add documents, archive
Templates 6 List, get, instantiate, save from workbook, swap sources, shared templates
Workspaces 6 List, get, create, delete, grants
User Attributes 9 CRUD, user/team/tenant value assignments
Webhooks 6 Webhook subscription management, payload signature validation, event history
Grants 5 Access control lists, workbook/workspace/connection grants
Files & Folders 4 Inode search, create folder, update, delete
Tags 4 List, create, tag workbook, tag data model
Reference 4 sigma_api_capabilities, sigma_formula_pitfalls, sigma_search_docs, sigma_get_doc_page
Composite Recipes 14 High-level multi-step workflow recipes

Note: Domain categories overlap slightly. The 2 bulk-destructive tools (sigma_bulk_deactivate_members, sigma_bulk_remove_team_members) are excluded by default and bring the total to 157 when enabled.


🍳 Composite Workflow Recipes

These high-level tools bundle multi-step API sequences into a single atomic call:

Recipe Tool What It Does
sigma_deploy_template_to_folder Instantiates a template & swaps warehouse sources in 1 call
sigma_materialize_and_wait Triggers a data materialization and polls until complete with timeout
sigma_onboard_member Atomically creates a member and assigns them to multiple teams
sigma_bulk_assign_team_members Batch-adds $N$ members to a team in a single request
sigma_bulk_remove_team_members Resolves member emails and batch-removes them from a team
sigma_bulk_deactivate_members Regex-matches members, generates dry-run report, and deactivates
sigma_bulk_sync_tenant_connections Performs RFC 8693 token exchange per tenant to sync all connections
sigma_copy_workbook_to_member Duplicates a workbook directly into a user's home folder
sigma_promote_workbook Tags a workbook for version promotion (creates tag if missing)
sigma_export_and_download Exports workbook/element, handles 204 polling, returns final content
sigma_sync_all_tables_in_schema Syncs an entire database.schema path across Sigma connections
sigma_reassign_workbook_ownership Bulk-transfers workbook ownership from one member email to another

📐 MCP 2.0 Hints & Safety Annotations

Every tool includes structured MCP hints to assist AI clients with user permission prompts:

Annotation Count Meaning
readOnlyHint=true 83 Indicates intended non-mutation; clients may still require explicit user approval
destructiveHint=true 16 Deletes, deactivates, or revokes; clients should prompt
idempotentHint=true 8 Safe to retry; same input = same outcome
openWorldHint=true 155 All tools hit an external API

🧮 Writing Sigma Formulas

AI models frequently hallucinate SQL or Excel functions when writing Sigma formulas (e.g. using ArrayAgg() instead of List()).
Before writing any Sigma formula, call the built-in reference tool:

# Model prompt helper
Use tool `sigma_formula_pitfalls` to check formula syntax rules.

See docs/formulas.md for full syntax details.


👩‍💻 Local Development & Testing

# Install dev tools
pip install -e ".[dev]"

# Run full test suite with 100% statement line coverage enforcement
pytest --cov=src/sigma_mcp --cov-fail-under=100 --cov-report=term-missing

# Run OpenAPI drift check
python scripts/check_openapi_drift.py

# Run MCP tool contract validation
python scripts/check_tool_contract.py

# Code formatting & type checking
ruff check src/
ruff format --check .
mypy --strict src/

🤝 Contributing & Community

Contributions are welcome! Please read CONTRIBUTING.md for development rules, SECURITY.md for security reporting, and CODE_OF_CONDUCT.md for community standards.


📜 License

MIT License.
Copyright (c) 2026 Christian Claudio.

Disclaimer: Not affiliated with, sponsored by, or endorsed by Sigma Computing, Inc.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选