MCP server · SandboxAQ

sandboxaq-mcp

Open endpoint → SandboxAQ provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: SandboxAQ Type: Hosted endpoint Transport: http Host: mcp.{tenant}.aisim.sandboxaq.com

Endpoint

https://mcp.{tenant}.aisim.sandboxaq.com

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "sandboxaq": { "url": "https://mcp.{tenant}.aisim.sandboxaq.com" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "sandboxaq": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.{tenant}.aisim.sandboxaq.com"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://mcp.{tenant}.aisim.sandboxaq.com \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

aqcat — Fully automated dense adsorption energy screening. Returns the lowest binding energy across placements — with per-placement convergence status — for a given bulk material, adsorbate and crystal facet. Powered by the AQCat25-EV2 machine-learning potential.
AqpotencyPotency — Predict pIC50 potency for a single protein-ligand pair from a UniProt accession and a ligand SMILES string. Bulk submission is not supported.
AqpotencyScreen — Score an uploaded SMILES library (up to 10,000 SMILES) against a single target for virtual screening. Results are returned sorted by potency_mean descending.
AqpotencyScan — Screen one ligand against a curated target panel for reverse screening and off-target triage. Panels are bundled in the container image — no external API calls at runtime.
AqpotencySelectivity — Compute on-target vs off-target potency and fold_selectivity for one ligand against one on-target and a list of off-targets.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.