MglennP Radial Switchboard
64-bit MGLE-NNP zero-auth MCP & A2A matchmaker, poison auditor, and 3-agent crew router.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"matchmaker": {
"url": "https://radialswitchboard.com/mcp"
}
}
}Remote-Endpunkte
https://radialswitchboard.com/mcpstreamable-httpWas es kann
Tool-Inventar
Tools (6)
🟢matchmake_agent_crew(intent, capabilities, mode, caller_region, require_instant_zero_auth, ...)
Rank live heartbeat-verified MCP and A2A endpoints using 64-bit MGLE-NNP bitwise capability masks and return either a provider-diverse shortlist or a 3-agent complementary crew (Compute + Domain + Verifier) with single-use execution tickets. Use when selecting callable agents for a task; use search_agent_directory for raw keyword browsing or get_agent_dossier when you already have an agent_id.
Eingabe-Schema
{
"type": "object",
"properties": {
"intent": {
"type": "string",
"description": "Natural-language task intent used to infer required 64-bit capability switches when capabilities is omitted."
},
"capabilities": {
"type": "array",
"description": "Optional explicit MGLE-NNP capability switch names (e.g. sql, database, finance_data, file_parse, math_verify, code_exec, web_fetch, search_rag).",
"items": {
"type": "string",
"description": "Canonical capability switch identifier from Bits 0..23."
}
},
"mode": {
"type": "string",
"enum": [
"top10_varied",
"crew"
],
"description": "Routing policy: 'top10_varied' for ranked shortlist across distinct vendors, or 'crew' for a 3-role complementary triad."
},
"caller_region": {
"type": "string",
"enum": [
"E",
"W",
"U",
"P",
"GLOBAL"
],
"description": "Caller geographic zone for round-trip latency affinity ('E' US-East, 'W' US-West, 'U' Europe, 'P' APAC, 'GLOBAL' any)."
},
"require_instant_zero_auth": {
"type": "boolean",
"description": "True (default: true) restricts results strictly to open zero-credential endpoints with verified non-zero tools/list schemas callable immediately without API keys or OAuth."
},
"max_latency_grade": {
"type": "string",
"enum": [
"A",
"B",
"C",
"D",
"ANY"
],
"description": "Worst acceptable Virginia Scout RTT grade ('A' <=120ms, 'B' <=300ms, 'C' <=700ms default, 'D' <=1500ms, 'ANY' unrestricted live RTT)."
},
"top_k": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Maximum number of ranked candidates to return (1..25, default 10)."
}
}
}Ausgabe-Schema
{
"type": "object",
"properties": {
"mode": {
"type": "string",
"description": "Applied routing policy identifier."
},
"finalist_count": {
"type": "integer",
"description": "Number of matched endpoints returned."
},
"scanned_pool_count": {
"type": "integer",
"description": "Total audited phonebook records scanned."
},
"finalists": {
"type": "array",
"description": "Ranked candidate agent records including endpoint URL, 64-bit hex ID, and execution_ticket.",
"items": {
"type": "object"
}
}
},
"required": [
"mode",
"finalist_count",
"finalists"
]
}🟢search_agent_directory(query, grade_filter, limit)
Browse and filter the audited Radial Switchboard phonebook by keyword substring and Virginia Scout health grade without consuming matchmaking call quota. Use when exploring catalog coverage by name, vendor, or grade; use matchmake_agent_crew instead when ranking capability-matched finalists for execution.
Eingabe-Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional case-insensitive keyword filter matched against agent_id, name, description, and endpoint URL."
},
"grade_filter": {
"type": "string",
"enum": [
"AB",
"A",
"B",
"C",
"D",
"ALL"
],
"description": "Filter by Virginia Scout audit grade ('AB' live <=350ms default, 'A' <=150ms, 'B' <=350ms, 'C' <=700ms, 'D' offline code, 'ALL' every non-poison record)."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Maximum number of directory records to return (1..50, default 20)."
}
}
}Ausgabe-Schema
{
"type": "object",
"properties": {
"total_matching": {
"type": "integer",
"description": "Total phonebook records matching the filter."
},
"returned_count": {
"type": "integer",
"description": "Number of records included in agents."
},
"agents": {
"type": "array",
"description": "Matching directory records with grade, coupler, and endpoint metadata.",
"items": {
"type": "object"
}
}
},
"required": [
"total_matching",
"returned_count",
"agents"
]
}🟢get_agent_dossier(agent_id)
Retrieve the complete 4-point Virginia Scout runtime heartbeat audit, measured RTT latency, 64-bit MGLE-NNP coupler breakdown, and SHA-256 tool-schema hash for one exact agent_id. Use only when inspecting a known agent_id; use search_agent_directory if you need to find the agent_id first.
Eingabe-Schema
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Exact agent or MCP server identifier from the Radial Switchboard phonebook (e.g. 'mcp://...' or registry slug)."
}
},
"required": [
"agent_id"
]
}Ausgabe-Schema
{
"type": "object",
"properties": {
"found": {
"type": "boolean",
"description": "True when agent_id exists in the audited phonebook."
},
"agent_id": {
"type": "string",
"description": "Requested agent identifier."
},
"dossier": {
"type": "object",
"description": "Full runtime audit record, coupler code, and schema hash."
}
},
"required": [
"found",
"agent_id"
]
}🟢get_switchboard_telemetry(include_recent_activity)
Return global US-EAST4 switchboard health, Grade A/B/D/E/F pool counts, autonomous registry crawl cursor state, and external hook telemetry. Use for system-wide status and pool metrics; use get_agent_dossier for an individual agent.
Eingabe-Schema
{
"type": "object",
"properties": {
"include_recent_activity": {
"type": "boolean",
"description": "Public privacy protection strips raw caller User-Agent/IP entries by default (default false); only recent_activity_count is returned publicly."
}
}
}Ausgabe-Schema
{
"type": "object",
"properties": {
"status": {
"type": "string",
"description": "Service operational state ('ok')."
},
"spec_version": {
"type": "string",
"description": "Active Radial Switchboard specification revision."
},
"total_unsorted_pool": {
"type": "integer",
"description": "Total indexed MCP and A2A records."
},
"live_callable_ab": {
"type": "integer",
"description": "Count of live verified Grade A and Grade B endpoints."
}
},
"required": [
"status",
"spec_version",
"total_unsorted_pool",
"live_callable_ab"
]
}🟡register_agent_endpoint(endpoint, agent_id, description)
Submit a public HTTPS MCP or A2A endpoint for immediate live SSRF-guarded Virginia Scout interrogation, 64-bit MGLE-NNP grading, and directory indexing. Use when enrolling a new server or appealing a quarantined grade; do not use for private localhost/RFC1918 URLs.
Eingabe-Schema
{
"type": "object",
"properties": {
"endpoint": {
"type": "string",
"description": "Publicly reachable HTTPS MCP or A2A endpoint URL to interrogate in real time."
},
"agent_id": {
"type": "string",
"description": "Optional canonical slug or identifier (e.g. 'com.example/my-mcp'); generated automatically if omitted."
},
"description": {
"type": "string",
"description": "Optional summary of capabilities or reason for re-audit."
}
},
"required": [
"endpoint"
]
}Ausgabe-Schema
{
"type": "object",
"properties": {
"registered": {
"type": "boolean",
"description": "True when SSRF validation passed and live interrogation completed."
},
"appeal_id": {
"type": "string",
"description": "Audit log reference ID."
},
"audit_status": {
"type": "string",
"description": "Assigned Virginia Scout runtime audit status."
},
"updated_record": {
"type": "object",
"description": "Resulting phonebook record and 64-bit coupler."
}
},
"required": [
"registered",
"audit_status"
]
}🟡report_execution_outcome(agent_id, execution_ticket, outcome_success, observed_latency_ms)
Submit a single-use HMAC execution_ticket from matchmake_agent_crew to record empirical downstream task completion or failure (+0.05 clean delivery / -0.20 timeout or schema failure on Byte-2 Guarantee grade). Use after invoking a matched agent to close the quality feedback loop.
Eingabe-Schema
{
"type": "object",
"properties": {
"agent_id": {
"type": "string",
"description": "Target agent_id that executed the downstream call."
},
"execution_ticket": {
"type": "string",
"description": "Single-use HMAC execution_ticket issued by matchmake_agent_crew."
},
"outcome_success": {
"type": "boolean",
"description": "True if the downstream agent fulfilled its schema contract cleanly; false on timeout, HTTP error, or malformed output."
},
"observed_latency_ms": {
"type": "number",
"minimum": 0,
"description": "Optional caller-observed round-trip execution latency in milliseconds."
}
},
"required": [
"agent_id",
"execution_ticket",
"outcome_success"
]
}Ausgabe-Schema
{
"type": "object",
"properties": {
"ticket_valid": {
"type": "boolean",
"description": "True when the single-use HMAC ticket passed verification and updated telemetry."
},
"agent_id": {
"type": "string",
"description": "Evaluated target agent_id."
}
},
"required": [
"ticket_valid"
]
}Community
Nachweis