How does JEV select evidence?

It filters twice: once at the search-result level before fetching pages and once at the content-block level after parsing, so pages that never make the first cut are not fetched and surviving blocks are trimmed before reaching the downstream model.

Why filter results instead of passing them through?

The project's premise is that dumping 20 full search results into an expensive downstream context window wastes tokens. Selecting evidence semantically first keeps the context compact while preserving provenance for each block.

What does the research tool return?

The README's flow shows the tool returning sources with title, URL, domain and evidence blocks, plus metadata, after context restore, deduplication and a token budget are applied.

Is it hosted or self-hosted?

Self-hosted and local-first per its own description: you run the Apache-2.0 MCP server yourself and point an MCP client at it. The digest does not show install commands or hosting requirements.

What does it need to run?

An MCP client and access to TypeSafe JEV, since the description says evidence is selected with TypeSafe JEV. The digest excerpt truncates before configuration, so key setup, providers and supported search backends are not evidenced.

What is JEV Research MCP status?

GitHub metadata shows 3 stars and one fork, created and pushed 2026-10-03, so activity is limited to its creation date. It is listed on Product Hunt as JEV Evidence MCP, and the digest shows no benchmarks or cost figures.

Jev directory

CommunityJev Agents & MCP

JEV Research MCP

A self-hosted MCP server that uses TypeSafe JEV as a semantic evidence-selection layer for coding-agent web research: it filters search results before fetching and parsed content blocks afterward, returning compact evidence blocks with provenance.

See highlights Open github.com

Stars: 3
Language: Python
License: APACHE-2.0
Reading time: 2 min
Published by: Community
Author: Merth1470
Last verified: Oct 2026

merth1470/jev-research-mcp

User repository on GitHub

View on GitHub

JEV Evidence MCP is a self-hosted, local-first Model Context Protocol (MCP) (https://modelcontextprotocol.io) server for coding-agent web research. Instead of dumping 20 full search results into an expensive downstream LLM context window, it selects evidence semantically with TypeSafe JEV.

Forks: 1
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity github mcp python research

Works forJev for Extraction Jev for Document processing

Used inJev for Software & DevTools

Languages: Python
Platforms: MCP
Capabilities: Open sourceSelf-hostedRuns locallyRequires API key

Highlights

Apache-2.0, self-hosted MCP server exposing one primary tool, research, for coding-agent web research.
Filters twice with TypeSafe JEV: at the search-result level before fetching and at the content-block level after parsing.
Returns compact evidence blocks with provenance plus metadata, instead of 20 full search results in the downstream context.
Flow: search, JEV result filter, fetch, parse, JEV block filter, context restore, dedup, token budget, sources.
GitHub metadata: created and pushed 2026-10-03, one fork; listed on Product Hunt as JEV Evidence MCP.

Watch out

README and GitHub metadata reviewed 2026-10-17; the excerpt truncates inside the research tool's flow description, so setup, provider configuration, costs and benchmarks are not evidenced. The repo shows activity only on its creation date.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Jev in front of the HeyGen MCP

X: Playwright CLI + Jev vs Playwright MCP

X: A local MCP server that cuts computer use from 23s to 0.8s. Cartwright built Cortex, a local MCP server where…

X: A side panel that drives any site's WebMCP tools

From the Jev guides

Original write-ups on what this entry is for.

MCP tool routing: Jev in front of the tool call

Oct 16, 2026

Tool menus can outgrow the context that reads them. The catalog's Jev-based routers and gates narrow the list: benchmarked tool search, per-tool scoring, fail-closed approvals, and WebMCP in the browser.

Jev Agents & MCP#mcp#tool-routing#agents

Read article

Approval policies for coding agents: hooks, guards, and gateways

Oct 16, 2026

How the Jev guard family turns coding-agent permissions into auto-approve, deny, or ask: hooks that enforce, guards that fail safe, and gateways that gate generation.

Jev Agents & MCP#coding-agents#guardrails#hooks

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai