Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

mcpmatch

Minimal demo that matches a user goal to the best MCP server or capability in a catalogue using Jev, in two stages for large catalogues.

MCP serverprototype
View on GitHub ↗

Overview

McpMatch takes a user's goal and matches it to the best MCP server or capability from a catalogue using TypeSafe's Jev, splitting the work into two stages when the catalogue is large, presumably a coarse shortlist followed by a final choice among the shortlisted options.

The README is a single line plus the install and run command, so the questions, catalogue format and staging details are not documented. It is a small demo of capability routing with typed choices.

What the decision model decides

TypeQuestionAnswers
ChoiceWhich MCP server or capability best matches this goal?—

How it works

  1. User states a goal
  2. For large catalogues, first stage shortlists candidates
  3. Second stage chooses the best match
  4. Result is displayed

Strengths

  • Two-stage approach for large catalogues

Caveats

  • Minimal documentation
  • Demo only

Getting started

npm i && npm run dev

At a glance

Type
MCP server
Status
prototype
Language
TypeScript
Runtime
web app
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

What does Jev decide?

Which MCP server or capability fits the user's goal.

Why two stages?

To handle large catalogues, per the description.

How do I run it?

npm i && npm run dev.

Related projects

  • jev-decision-layer

    MIT plugin and local MCP server that hands an agent's closed questions to Jev or local Laya, with policy gates and receipts.

    Agent skillproductionPython
  • agent-dispatcher

    Claude Code and Codex skill that routes a task to one of 27 specialist roles, with an optional Jev engine for catalog selection.

    ProjectbetaPython
  • Gatekeeper

    Claude Code hook that decides which agent or skill should handle a request using YAML rulebooks plus one Jev Choice with confidence bands.

    HookbetaPython
  • Helm

    Orchestrator that probes which coding agents are installed and logged in, then has Jev pick the best one for a task.

    Agent skillbetaPython
  • jev-agent-hooks

    Hooks for Claude Code, Codex and pi that use Jev to suggest a skill each turn, plus a rule gate for subagent model routing.

    HookbetaJavaScript
  • jev-pilot

    Claude Code plugin that asks Jev before each turn for reasoning effort, subagent model, strategy and skill, with a decision log.

    Agent skillbetaTypeScript