AI & Machine Learning
ivive.app
An MCP server for pharmacokinetic and IVIVE predictions from SMILES structures, including clearance, fraction unbound, and similar-drug comparisons.
ENDPOINT 1
https://api.ivive.app/mcp
MCP server metadata
- Name
- ivive
- Version
- 1.0.1
ADME/IVIVE calculations for early drug discovery. Do not compute clearance yourself: call these tools. Relay the warnings and caveats in each result to the user. Values from predict_inputs are predictions; when they feed another tool, say so. All results are research estimates, not for clinical, regulatory or dosing decisions; tell the user so.
Known tools 6
predict_inputsPredict fu,p and fu,inc from a SMILES, with structure-only human CL and Vss as second opinions.
Inferred read-onlycalc_clhepHepatic and plasma clearance from in-vitro CLint, fu,mic and fu,p (IVIVE), with the observed-CL band and applicability warnings.
Inferred read-onlytarget_clintThe in-vitro CLint an assay must read for a compound to reach a target plasma clearance.
Inferred read-onlysimilar_drugsMost similar reference drugs to a SMILES, with observed and IVIVE-predicted clearance: how IVIVE fared on this kind of structure.
Inferred read-onlyscale_to_humanPredict human plasma CL from observed animal in-vivo CL (rat, dog, monkey), every applicable method with its measured error.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.ivive]
url = "https://api.ivive.app/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"ivive": {
"type": "http",
"url": "https://api.ivive.app/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: ivive
Remote MCP URL: https://api.ivive.app/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"ivive": {
"url": "https://api.ivive.app/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ivive": {
"type": "http",
"url": "https://api.ivive.app/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "ivive",
"transport": "streamable-http",
"url": "https://api.ivive.app/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.