Odel
Cactus

Cactus

@pipeworx-ioTypeScriptMITUpdated 1w ago

NCI CACTUS Chemical Identifier Resolver MCP.

Server endpointStreamable HTTPNo authProbed

This is the third-party server itself — Odel doesn't run it. Hitting this URL directly talks straight to the upstream server with no auth or proxying. Connect through Odel to front it with managed auth.

mcp-cactus

NCI CACTUS Chemical Identifier Resolver MCP.

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Tools

ToolDescription
resolveNCI CACTUS chemical identifier resolver. Convert one chemical identifier (a drug/chemical name, CAS number, SMILES, InChI, or InChIKey) into a single representation: smiles (canonical SMILES), stdinchi (standard InChI), stdinchikey (standard InChIKey), iupac_name, names (synonym list), formula (molecular formula), mw (molecular weight), or cas (CAS registry number(s)). Keyless, plain-text API.
identifyNCI CACTUS one-shot lookup: given any chemical identifier (name, CAS, SMILES, InChI, or InChIKey), return SMILES, InChIKey, IUPAC name, molecular formula, molecular weight, and CAS number in a single call. Fields that cannot be resolved are returned as null. Keyless, plain-text API.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "cactus": {
      "url": "https://gateway.pipeworx.io/cactus/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/cactus/mcp returns the tools in the table above plus the shared Pipeworx meta-toolsask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1476+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Cactus data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT