AI-infrastructure (Neocloud) bond credit spread index: Composite/HY/IG levels, series, attribution.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Get this week's index change attribution (which bonds moved the index, in bp).
This tool takes no arguments.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http ncsx https://spreadbench.com/mcp
Get this week's index change attribution (which bonds moved the index, in bp).
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Get the profile and 30-day spread path of one constituent bond by CUSIP (e.g. US21873SAC26).
| Argument | Type | Description |
|---|---|---|
| cusip* | string | 9-character CUSIP, e.g. US21873SAC26 |
{
"type": "object",
"required": [
"cusip"
],
"properties": {
"cusip": {
"type": "string",
"pattern": "^[A-Z0-9]{9}$",
"description": "9-character CUSIP, e.g. US21873SAC26"
}
},
"additionalProperties": false
}List all constituent bonds (issuer, coupon, maturity, rating, tier, spread) with identifier verification status.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Get the latest NCSX index levels (Composite / HY / IG) with daily & weekly changes, 90-day percentiles, as-of date, methodology version, DOI and data_status. Read data_status before quoting: "seed" means demo series, "verified" means observed market data.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Get the 90-trading-day daily level series for one NCSX index tier (composite | hy | ig).
| Argument | Type | Description |
|---|---|---|
| tier* | string | Index tier: composite, hy, or ig |
{
"type": "object",
"required": [
"tier"
],
"properties": {
"tier": {
"enum": [
"composite",
"hy",
"ig"
],
"type": "string",
"description": "Index tier: composite, hy, or ig"
}
},
"additionalProperties": false
}Get methodology metadata: version, DOI, license, formulas, data source licensing status.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Get the latest weekly report snapshot (levels, weekly changes, attribution, citation string).
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 3, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.