Deterministic SHA-256 collateral checks, optical forensics, and ZK provenance proofs.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Scoped sandbox key (free discovery) or paid production key for ZK & batch tools.
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.
Execute Merton jump-diffusion tail LTV haircuts across collateral portfolios.
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.
Run in a terminal
claude mcp add --transport http mcp-server https://mcp.ariadnenexus.com/mcp
Headers
X-API-Key (optional, not in the config above): Scoped sandbox key (free discovery) or paid production key for ZK & batch tools.Execute Merton jump-diffusion tail LTV haircuts across collateral portfolios.
| Argument | Type | Description |
|---|
| assets* | array |
{
"type": "object",
"required": [
"assets"
],
"properties": {
"assets": {
"type": "array"
}
}
}Generate Ed25519-signed Zero-Knowledge collateral provenance attestation.
| Argument | Type | Description |
|---|---|---|
| asset_id* | string | |
| policy_ref* | string |
{
"type": "object",
"required": [
"asset_id",
"policy_ref"
],
"properties": {
"asset_id": {
"type": "string"
},
"policy_ref": {
"type": "string"
}
}
}Inspect canonical ANX-RFC-001 collateral manifest schema and optical fields.
| Argument | Type | Description |
|---|---|---|
| collateral_class | string |
{
"type": "object",
"properties": {
"collateral_class": {
"type": "string"
}
}
}Deterministic SHA-256 collateral manifest verification under 42ms p99 latency.
| Argument | Type | Description |
|---|---|---|
| asset_sha256* | string | |
| collateral_class | string |
{
"type": "object",
"required": [
"asset_sha256"
],
"properties": {
"asset_sha256": {
"type": "string"
},
"collateral_class": {
"type": "string"
}
}
}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 17, 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.