madjik-io/mcp-server
Quantum-finance market metrics for AI agents, computed by the Black Belt Labs engine.
Connector by madjik-io · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/madjik-io-mcp-server
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 6 read · 0 write · 0 deleteRead-only
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 6
Read from the source code; the running server may list different tools.
Read 6 · Look things up without changing anything.
get_ai_metricsget_metricget_quantum_metricsget_risk_snapshotlist_metricssearch_metrics
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
MADJIK_API_KEY
Tools (6)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
get_ai_metricsFetch all AI-enhanced metrics: Sentiment (M50017), Market Narrative (M50019), Anomaly Detection (M50020), Regime Detection (M50016), and Regulatory Risk (M50010). All computed via Gemini on Vertex AI.
get_metricFetch the current value, signal, and metadata for a single Madjik metric by ID (computed by Black Belt Labs). Use list_metrics or search_metrics first to find the right metric ID.
get_quantum_metricsFetch all quantum-computed metrics: Portfolio Optimisation (M50021) and Risk Simulation VaR (M50022). These are the flagship Black Belt Labs QC outputs.
get_risk_snapshotFetch a composite risk snapshot combining QC VaR (M50022), Leverage Stress (M50002), Liquidation Cascade Risk (M50004), and Correlation Breakdown (M50003). Use this for a fast single-call risk assessment.
list_metricsList all available Black Belt Labs metrics with their IDs, names, categories, computation method (quantum / ai / classical), and descriptions.
search_metricsSearch Black Belt Labs metrics by keyword. Searches metric names, descriptions, and categories.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- Aug 30, 2026 (1 month ago)
- Last release
- Aug 31, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.madjik-io/mcp-server- Version
- 2.0.2
- Auth
- API key
- Packages
- npm madjik-mcp-server
- License
- MIT
- Repository
- github.com/madjik-io/mcp-server
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
madjik-io/mcp-server. Agent Mart. https://agentmart.dev/connectors/madjik-io-mcp-server (last updated 2026-10-24)