By metatateai
Use Metatate structured context and policy decisions from Claude Code through Snowflake-managed MCP.
Ask Metatate whether a proposed data use is allowed, denied, conditional, or unknown.
Find governed Metatate assets by database, schema, domain, sensitivity, PII status, or compliance tag.
Explain a prior Metatate authorization decision or query validation.
Explain governed data meaning, classification, sensitivity, PII, and masking facts for a table or column.
Inspect active governance, usage, validation, and transfer rules for a governed asset.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Bring Metatate's structured context and decision layer into Claude Code.
Metatate gives agents structured, machine-readable context for data workflows:
data meaning, business logic, policies, lineage, access rules, runtime
conditions, and decision evidence. The metatate plugin lets Claude Code query
that context through the Snowflake-managed MCP server installed by the Metatate
Snowflake Native App.
Claude Code remains the developer workspace. Metatate remains the source of truth for governed data context, intended-use validation, authorization decisions, explanations, and audit evidence. This plugin does not run a Metatate-hosted MCP gateway and it does not store Snowflake credentials in the plugin repository.
metatate-claude-plugins/
.claude-plugin/
marketplace.json
plugins/
metatate/
.claude-plugin/
plugin.json
bin/
metatate-mcp-add
commands/
skills/
README.md
docs/
claude-code-install.md
snowflake-admin-setup.md
troubleshooting.md
examples/
prompts.md
SECURITY.md
CHANGELOG.md
LICENSE
For the Snowflake administrator:
METATATE_APP.CORE.METATATE_MCP.For each Claude Code user:
In Claude Code, add this public marketplace:
/plugin marketplace add metatateai/metatate-claude-plugins
Install the Metatate plugin:
/plugin install metatate@metatate-claude-plugins
Restart Claude Code after installation if Claude prompts you to do so.
The plugin and the MCP connection are separate:
If you cloned this repository locally, register the MCP server with the helper. Replace the placeholders with values from your Snowflake administrator:
./plugins/metatate/bin/metatate-mcp-add \
--account-url https://<account-url> \
--client-id <snowflake-oauth-client-id> \
--snowflake-role <snowflake-role> \
--config-scope user \
--run
Claude Code will prompt for the OAuth client secret. Do not paste the client secret into a shell command, README, issue, ticket, or committed file.
The session:role:<snowflake-role> scope is required. It makes Snowflake issue
the OAuth session for the intended Metatate role instead of falling back to the
user's default role or secondary role ALL.
The helper generates the equivalent claude mcp add-json command:
claude mcp add-json --scope user --client-secret metatate '{
"type": "http",
"url": "https://<account-url>/api/v2/databases/METATATE_APP/schemas/CORE/mcp-servers/METATATE_MCP",
"oauth": {
"clientId": "<snowflake-oauth-client-id>",
"callbackPort": 8080,
"scopes": "session:role:<snowflake-role>"
}
}'
The JSON payload in that command is:
{
"type": "http",
"url": "https://<account-url>/api/v2/databases/METATATE_APP/schemas/CORE/mcp-servers/METATATE_MCP",
"oauth": {
"clientId": "<snowflake-oauth-client-id>",
"callbackPort": 8080,
"scopes": "session:role:<snowflake-role>"
}
}
Start Claude Code and open the MCP menu:
/mcp
npx claudepluginhub metatateai/metatate-claude-plugins --plugin metatateComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.