AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Runcontext

mcp-quiet-victory-labs-runcontext · by Quiet-Victory-Labs

Tell your AI agent to build your semantic layer. Open-source CLI for database introspection, metadata governance, and MCP serving. Built on OSI.

No reviews yet
0 installs
30 views
0.0% view→install

Install

$ agentstack add mcp-quiet-victory-labs-runcontext

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-quiet-victory-labs-runcontext)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Runcontext? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

RunContext

Turn your database into an AI-ready semantic plane.

Run context setup, connect your database, and RunContext introspects the schema to scaffold a semantic plane — structured metadata that tells AI agents what your data means, how to query it safely, and which business rules apply. Then hand off to your AI agent to curate it to Gold. Serve it via MCP to Claude Code, Cursor, Copilot, or any compatible tool.


Quick Start

npx @runcontext/cli setup

A browser wizard opens. Connect your database, fill out the Context Brief, and RunContext scaffolds your semantic plane automatically.


How It Works

The context setup wizard walks you through six steps:

| Step | What happens | |------|-------------| | 1. Connect | Connect to your database | | 2. Define | Name your semantic plane, set owner and sensitivity | | 3. Scaffold | Auto-introspect schema and generate Bronze-tier metadata | | 4. Checkpoint | Review what was built | | 5. Curate | Hand off to your IDE's AI agent to curate metadata to Gold using real data queries | | 6. Serve | Start the MCP server and serve your semantic plane to AI tools |

The result is a context/ directory of YAML files following the OSI (Open Semantic Interchange) specification.


Tiers

Bronze -- Scaffolded automatically. Every model and field has a description, owner, and type. Your data is discoverable.

Silver -- Sample values, tags, and richer descriptions. AI agents can interpret the data with confidence.

Gold -- Golden queries, guardrails, semantic roles, and business rules. Agents generate correct SQL on the first try.

Check your progress with context tier.


Commands

context setup                  # Browser wizard -- database to semantic plane
context tier [model]           # Bronze/Silver/Gold scorecard
context serve                  # Start MCP server (stdio for IDE integration)
context lint                   # Validate metadata
context fix                    # Auto-fix lint issues
context verify                 # Check metadata against live database
context build                  # Compile context layer to manifest
context dev                    # Watch mode
context introspect             # Schema introspection
context explain [term]         # Look up models, terms, or owners

MCP Server

Add RunContext to your AI tool's MCP configuration:

{
  "mcpServers": {
    "runcontext": {
      "command": "npx",
      "args": ["@runcontext/cli", "serve", "--stdio"]
    }
  }
}

6 MCP tools available:

| Tool | Description | |------|-------------| | context_search | Find models, datasets, and fields by keyword | | context_explain | Get full model details | | context_validate | Run the linter | | context_tier | Get tier scorecard | | context_golden_query | Find validated SQL queries | | context_guardrails | Get WHERE clauses and access rules for tables |

Works with Claude Code, Cursor, Copilot, Windsurf, Claude Desktop, and any MCP-compatible tool.


Database Support

| Database | Supported | |----------|-----------| | PostgreSQL | Yes | | DuckDB | Yes | | MySQL | Yes | | SQL Server | Yes | | SQLite | Yes | | Snowflake | Yes | | BigQuery | Yes | | ClickHouse | Yes | | Databricks | Yes |


Packages

| Package | Description | |---------|-------------| | @runcontext/cli | CLI, setup wizard, and MCP server | | @runcontext/core | Compiler, linter, tier engine, adapters | | @runcontext/mcp | MCP protocol implementation | | @runcontext/ui | Browser-based setup wizard and planes viewer | | @runcontext/uxd | Design system components | | @runcontext/db | Database utilities | | create-runcontext | Project scaffolder (npx create-runcontext) |


Links

License

MIT

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.