shipwithjev

Catalog / Agents & browsers

0023GitHub

jev-tool-router

Picks the MCP tool for Codex, instead of listing them all.

The router asks Jev which tool a step needs and passes that one on, so the agent’s context does not carry every tool definition it might use.

jackbarunz/jev-tool-routerREADME ↗
# Jev Tool Router

Jev-powered MCP tool routing for Codex.

Unofficial community project. Not affiliated with or endorsed by TypeSafe AI,
Vercel, or OpenAI.

Instead of exposing hundreds of external MCP tool schemas directly to the
agent, Jev Tool Router exposes a small routing surface and resolves external
tool discovery on demand.

The core flow is:

    agent: "I need capability X"
                  |
                  v
        jev_router/find_tool
                  |
                  v
      Jev sees request + tool
        names + descriptions
                  |
          +-------+-------+
          |               |
      >= threshold     uncertain/error
          |               |
          v               v
    one tool + schema  compact shortlist
          |               |
          v               v
       call tool      targeted search
                          |
                          v
                    paginated expand
                          |
                          v
                  full list only last

Default selection threshold: 0.90.

## Why

Large MCP setups can expose hundreds of tool definitions to an agent even when
only one tool is relevant to the current task. This project moves external MCP
tool discovery behind a small router:

- find_tool
- get_tool_schema
- search_tools
- list_servers
- list_tools
- list_all_tools
- call_readonly_tool
- call_tool
- evaluate_work_with_jev
- router_status

The underlying tool inventory remains available. The router narrows discovery;
it does not permanently remove the fallback path.

## What Jev does

For routing, Jev receives:

- the capability the agent is looking for
- optional task context
- tool names
- tool descriptions

It does not receive every full input schema during routing.

Every r

Also filed under Agents & browsers

  1. 0226

    Flight search with Browser Use★

    Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

    @gregpr07 · Agents & browsers · ~$0.004 · ~7 s

  2. 0619

    jevmem: automatic project memory for Claude Code

    After every Claude Code message, Jev decides in ~0.3 s whether it holds a decision, rule or bug worth keeping, and jevmem saves it as one line in JEVMEM.md.

    @jetwaniavinash · Agents & browsers · ~0.3 s

  3. 0618

    Playwright + Jev: tests in plain language

    Write Playwright steps like "add the most expensive item to the cart". Jev finds the right buttons and fields, fills forms and checks the result.

    Andrey Popov · Agents & browsers

  4. 0617

    toolgate: a tool-call firewall for agents

    A Claude Code and MCP hook where Jev answers seven yes/no risk questions per tool call to allow, ask or deny. Usage and benchmark numbers are in the repo.

    Jaz · Agents & browsers