catalog
Server Details
Search avva for an expert's Decision Model, then connect it: judgment from real past decisions.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
fetch and search have clearly distinct roles: one retrieves a full card by specific id, the other discovers relevant ids by query. There is no overlap or ambiguity between the two tools.
Both tools use simple, imperative verb names (fetch, search) that match their read-only actions. The naming pattern is consistent and immediately understandable.
With only two tools, the set is minimal but appropriate for a read-only expert catalog whose core workflow is discover-then-fetch. It is slightly thin but not unreasonable for the stated purpose.
The search-to-fetch workflow covers the essential catalog lifecycle: finding experts and retrieving full details. Minor gaps such as browsing categories or related experts exist but are not critical for the domain.
Available Tools
2 toolsTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Find people with real experience. Bring their approved workflows and decisions into your agent.
Governed decision engine: yes/no, score, choice and rank answers about cases, from past outcomes.
Multi-expert decision intelligence with transparent synthesis and auditable workflows.
Ask AI minds of real, named experts: answers, workflows and critiques in their judgment.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceConnects AI coding agents to the Jev decision model, enabling fast and cheap structured decisions such as task classification, strategy selection, complexity rating, and escalation decisions.MIT

Xzar MCP Serverofficial
AlicenseAqualityBmaintenanceCrash-test AI agents on real professional decisions. Agents take real tariff classification and patent examination cases, search reference libraries and rulebooks, submit a decision, and get an exact score with a receipt against what the professional actually decided. Most cases were decided after current models were trained.9MIT- AlicenseNot gradedqualityCmaintenanceEnables agents to delegate decisions to a configurable model, returning recommended choices with percentage scores and profile-based routing.11 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables any agent to ask typed questions (Noul, Choice, Score) against Jev's decision model and receive structured answers with probabilities, confidence, and an auditable act/review/abstain decision.49 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.