A
licenseNot graded
qualityB
maintenanceEnables Codex to run shadow-mode evidence selection by reading source files, scoring passage relevance with Jev or local Eve models, and returning original text with provisional exclusion decisions.
MIT
Awesome JEV
Server Details
Search Jev / System One projects and read their recorded inclusion evidence.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- daftAI2026/awesome-jev
- GitHub Stars
- 14
- ChatGPT
- –
- Claude
- –
TDQS
A4/5.0
Scored across 2 tools
Disambiguation5/5
The two tools split cleanly along the retrieve-one vs find-many axis: get_project fetches a single project by identity, while search_projects queries the collection. There is no overlap or plausible misselection between them.
Naming Consistency5/5
Both names follow the same verb_noun snake_case pattern (get_project, search_projects). The verbs are precise and conventionally paired with the plural/singular noun forms, making the set highly predictable.
Tool Count3/5
For a read-only public project directory, search plus fetch is the minimal viable surface, but two tools is thin — there is no separate enumeration tool for categories, tags or languages. The count is defensible yet borderline under-scoped.
Completeness4/5
Core discovery workflows are covered: keyword/category/tag/language search with bounded pagination, plus single-project retrieval with identity resolution. Minor gaps remain around enumerating available categories/tags/languages or traversing result sets beyond bounded snapshot pages.
Available Tools
2 toolsget_projectGet a projectARead-onlyIdempotentInspect
Read one public GitHub project and its inclusion evidence. Resolves known old addresses; missing or hidden identities return null.
Inputs: identity (required).
search_projectsSearch Awesome JEV projectsARead-onlyIdempotentInspect
Find public Jev / System One projects by keyword, category, tag or language. Returns bounded pages from a build snapshot.
Inputs: tag, page, sort, limit, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Related MCP Connectors
Review agent task evidence with sample deduplication, version filters and uncertainty intervals.
Read recorded npm loading evidence across pinned Node.js, Bun and Deno runtimes.
Search robot code and exact-version findings; check evidence before preparing with the Hub CLI.
Read bounded illicit-economy evidence with provenance, privacy, availability, and federation intact.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables screening of article titles and abstracts against a research question or clinical query using TypeSafe Jev, returning include/maybe/exclude decisions with calibrated probabilities from PubMed searches, PMIDs, or custom records.32MIT
- AlicenseNot gradedqualityCmaintenanceEnables Claude to cheaply bulk-screen 30 or more short items (repo blurbs, issue titles, log lines, grep hits, test names) against one crisp yes/no criterion, using Jev to sort them into clear_yes, uncertain and clear_no buckets instead of spending its own tokens on each. It supports inline items or a project-local .json/.jsonl file read server-side to keep context cost low, while treating results as advisory only.GPL 3.0
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to run source-bound evidence checks and bounded batch judgments for classification, extraction, and decision tasks via TypeSafe Jev.28 npmMIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.