Skip to content

Jev MCP Dispatcher

Proof-of-concept dispatcher that discovers an MCP server's tools at runtime with list_tools() and routes plain-language commands using only Jev Choice and Noul, with no general-purpose LLM calls.

Stars
4
Language
Python
Published by
Community
Author
abhishekashokvkumar
Last verified
Oct 2026

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.

Forks
1
Last pushed
Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Zero general-purpose LLM calls — anywhere in this pipeline, not for picking the tool, not for reading a parameter's value out of a sentence, not for anything. This is a proof of concept for a different way to do MCP tool dispatch: given a simple MCP (Model Context Protocol) server — one whose tools take primitive-typed parameters — this script dynamically discovers its tool signatures at runtime and uses Jev — TypeSafe's System One reasoning model — to route a plain natural-language command to the correct tool…

Quoted from the project's README. Read the full README.

Highlights

  • Tool selection is a Choice over live tool names and descriptions, returned as a confidence-scored ranking.
  • Non-enum arguments use one parallel per-word Noul pass; values are exact substrings copied from the command.
  • Word-form numbers gate one deterministic text2num rewrite; type conversion is plain Python casting.
  • Compound commands get a 1-to-5 Choice count and are split into spans that each rerun the pipeline.

Watch out

Only string, integer, number, boolean and enum parameters are supported; values must appear literally in the command, optional parameters are still force-extracted, and there is no confidence gating, retry or multi-turn clarification. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

14GitHub stars
Tiered agent memory keeping compact summaries with source links over searchable raw history, where a router decides per query whether notes suffice or raw pages must be recovered.
Jev Agents & MCP#community#jevbest#catalog-import
37GitHub stars
Python SDK that runs the same prompt, tools, and MCP setup across DeepAgents, Pydantic AI, Claude Agent SDK, Codex, and OpenCode by switching harness.
Jev Agents & MCP#community#jevbest#catalog-import
14GitHub stars
Opt-in Hermes plugin that routes each turn to one skill: a wide Jev Choice plus request checks gate a narrow fits round, injecting a single ignorable hint line.
Jev Agents & MCP#community#jevbest#catalog-import
LangChain deepagents middleware that replaces SkillsMiddleware with per-turn judging, loading only the SKILL.md files a turn needs so large catalogs stay out of the prompt.
Jev Agents & MCP#community#jevbest#catalog-import
4GitHub stars
A LangChain agent where Jev routes intent as a typed choice over four fixed criteria, with confidence below 0.6 falling back to local keyword rules, and each route carrying exactly one tool and one prompt.
Jev Agents & MCP#community#jevbest#catalog-import
14GitHub stars
Claude Code hook that asks Jev which installed skill fits each prompt and logs the answer, plus the script that joins that log to session transcripts and the negative result the author got from a week of running it.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai