io.github.Blite-HQ/qnexus-mcp MCP Server
io.github.Blite-HQ/qnexus-mcp
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.Blite-HQ/qnexus-mcp MCP server?
MCP server for Quantinuum Nexus, wrapping the qnexus SDK. Not affiliated with Quantinuum.
How to install io.github.Blite-HQ/qnexus-mcp
Copy-paste configuration for popular MCP clients.
QNEXUS_MCP_TOOLSETSComma-separated toolsets: read,execute,manage,destructive (default: read).
QNEXUS_MCP_ALLOW_SPENDPermit credit-spending (HQC) execution (default: false).
QNEXUS_MCP_ALLOW_HARDWAREPermit real-QPU targets (default: false).
QNEXUS_MCP_ALLOW_DESTRUCTIVEPermit delete/cancel/archive tools (default: false).
QNEXUS_MCP_MAX_CREDITSHard per-call HQC ceiling; 0 blocks all spend (default: 0).
QNEXUS_MCP_MAX_OUTCOMESTop-N cap on distinct measurement outcomes returned per result item (default: 100).
QNEXUS_MCP_MAX_SUBMISSIONS_PER_MINUTESliding-window submission cap; each circuit in a batch counts as one (default: 6).
QNEXUS_MCP_PROJECTSComma-separated project allowlist, enforced on every mutating tool (default: all projects).
{
"mcpServers": {
"qnexus-mcp": {
"command": "uvx",
"args": [
"qnexus-mcp"
],
"env": {
"QNEXUS_MCP_TOOLSETS": "<YOUR_QNEXUS_MCP_TOOLSETS>",
"QNEXUS_MCP_ALLOW_SPEND": "<YOUR_QNEXUS_MCP_ALLOW_SPEND>",
"QNEXUS_MCP_ALLOW_HARDWARE": "<YOUR_QNEXUS_MCP_ALLOW_HARDWARE>",
"QNEXUS_MCP_ALLOW_DESTRUCTIVE": "<YOUR_QNEXUS_MCP_ALLOW_DESTRUCTIVE>",
"QNEXUS_MCP_MAX_CREDITS": "<YOUR_QNEXUS_MCP_MAX_CREDITS>",
"QNEXUS_MCP_MAX_OUTCOMES": "<YOUR_QNEXUS_MCP_MAX_OUTCOMES>",
"QNEXUS_MCP_MAX_SUBMISSIONS_PER_MINUTE": "<YOUR_QNEXUS_MCP_MAX_SUBMISSIONS_PER_MINUTE>",
"QNEXUS_MCP_PROJECTS": "<YOUR_QNEXUS_MCP_PROJECTS>"
}
}
}
}Related MCP servers

Open Brain
Graph-structured MCP memory server with semantic search, auto-dedup, and knowledge synthesis.

x402nano
Machine-payable prediction-market briefs and probability-change monitoring for AI agents.

Amicus
Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.

Event Resolver API
Resolve prediction market events. Price checks, claim verification, outcome confidence.
Real-time market data, web search, and crypto intelligence for Claude—pay per call via USDC wallet.

io.github.BlogFactoryHQ/ghost-publisher
Local-first MCP server for safe Ghost authoring, diagnostics, scheduling, and publishing.
