Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An open-source MCP router for AI agents and MCP clients. It discovers, catalogs, classifies and deduplicates MCP servers and tools, then exposes each agent only the small, relevant, authorized subset it needs, plus routed Agent Skills.
How it uses Jev
Routing is a System One cascade: a Choice question picks the domain among those present, Score ranks surviving candidates, and a Noul no-match gate decides whether anything fits. Results are re-filtered by policy; model scores are relevance data and never widen access. Any model failure falls back to deterministic ranking.
Primitives:choicescorenoul
Technique worth stealing
Hierarchical cascade over a pre-filtered authorized scope, with a no-match gate and deterministic fallback, instead of one classification over the whole catalog.
Try it
cp .env.example .env, set MCPR_ADMIN_TOKEN and POSTGRES_PASSWORD, then docker compose up -d --build --wait; open http://localhost:8400/.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.67
- Shows a System One patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.10
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.90
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.86 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 21 Oct 2026.