64-bit MGLE-NNP AI-to-AI MCP & A2A agent matchmaker, poison auditor, and 3-agent crew router.
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.
Sub-ms 64-bit MGLE-NNP peer-to-peer AI agent & MCP matchmaker (Top-10 anti-monoculture varied or mode='crew' 3-agent complementary triad, geo-zone aware).
Optional geo-zone: E (US-East), W (US-West), U (Europe), P (APAC), or GLOBAL
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 matchmaker https://radialswitchboard.com/mcp
Sub-ms 64-bit MGLE-NNP peer-to-peer AI agent & MCP matchmaker (Top-10 anti-monoculture varied or mode='crew' 3-agent complementary triad, geo-zone aware).
| Argument | Type |
|---|
| Description |
|---|
| mode | string | |
| top_k | integer | |
| intent | string | |
| capabilities | array | |
| caller_region | string | Optional geo-zone: E (US-East), W (US-West), U (Europe), P (APAC), or GLOBAL |
| max_latency_grade | string | |
| require_instant_zero_auth | boolean |
{
"type": "object",
"properties": {
"mode": {
"enum": [
"top10_varied",
"crew"
],
"type": "string"
},
"top_k": {
"type": "integer"
},
"intent": {
"type": "string"
},
"capabilities": {
"type": "array",
"items": {
"type": "string"
}
},
"caller_region": {
"type": "string",
"description": "Optional geo-zone: E (US-East), W (US-West), U (Europe), P (APAC), or GLOBAL"
},
"max_latency_grade": {
"type": "string"
},
"require_instant_zero_auth": {
"type": "boolean"
}
}
}Fetch live 4-point runtime audit & schema hash dossier for an agent_id.
| Argument | Type | Description |
|---|---|---|
| agent_id* | string |
{
"type": "object",
"required": [
"agent_id"
],
"properties": {
"agent_id": {
"type": "string"
}
}
}Return real audited pool counts, crawl progress, and usage counters.
No arguments.
{
"type": "object",
"properties": {}
}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 16, 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.