Matchmake 64-Bit Agent Shortlist or 3-Agent Crew
matchmake_agent_crewRank 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.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "matchmake_agent_crew"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Routing policy: 'top10_varied' for ranked shortlist across distinct vendors, or 'crew' for a 3-role complementary triad. | |
| top_k | No | Maximum number of ranked candidates to return (1..25, default 10). | |
| intent | No | Natural-language task intent used to infer required 64-bit capability switches when capabilities is omitted. | |
| capabilities | No | Optional explicit MGLE-NNP capability switch names (e.g. sql, database, finance_data, file_parse, math_verify, code_exec, web_fetch, search_rag). | |
| caller_region | No | Caller geographic zone for round-trip latency affinity ('E' US-East, 'W' US-West, 'U' Europe, 'P' APAC, 'GLOBAL' any). | |
| max_latency_grade | No | Worst acceptable Virginia Scout RTT grade ('A' <=120ms, 'B' <=300ms, 'C' <=700ms default, 'D' <=1500ms, 'ANY' unrestricted live RTT). | |
| require_instant_zero_auth | No | 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. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | Applied routing policy identifier. | |
| finalists | Yes | Ranked candidate agent records including endpoint URL, 64-bit hex ID, and execution_ticket. | |
| finalist_count | Yes | Number of matched endpoints returned. | |
| scanned_pool_count | No | Total audited phonebook records scanned. |