AI & Machine Learning

jev-agent.com

An AI-powered evaluation server that scores resumes, grades essays or rubric-based submissions, and judges text with yes/no or multiple-choice probabilities.

1 endpoint7 known toolsFirst detected October 9, 2026Last detected October 9, 2026

ENDPOINT 1

https://jev-agent.com/api/mcp

No auth detected

MCP server metadata

Name: jagent
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

Jagent grades writing and checks resumes with Jev, a judgment model that returns calibrated probabilities instead of generated text. - check_resume: score a resume against a job posting (keyword coverage, ATS format checks, the chance a recruiter interviews). - grade_essay: class essays, Common App personal statements and SAT School Day essays, against built-in rubrics. - grade_with_rubric: one or many submissions against a teacher's own rubric. - judge_yes_no, judge_choice, judge_score: any yes/no, multiple-choice or rubric question about a text, answered with probabilities. - compare_versions: which of two versions is stronger, asked in both orders to cancel position bias. None of these tools write or rewrite text. Each call costs credits from the API key's balance (1 credit per 1,000 input tokens).

Known tools 7

check_resume

Score a resume, optionally against a job posting: a 0-100 match score, the posting's keywords found and missing (matched literally, as an ATS search would), ATS format checks, the level fit, and the probability a recruiter would move it to interview.

Inferred read-only

grade_essay

Grade one essay against a built-in rubric.

Inferred read-only

grade_with_rubric

Grade one or more submissions (up to 30, in parallel) against a rubric you supply: each criterion scored on a 3- to 6-point scale, summed per submission.

Inferred read-only

judge_yes_no

Ask any yes/no question about a text and get the probability that the answer is yes.

Inferred read-only

judge_choice

Pick the option that best fits a text, with a probability for every option and a confidence.

Inferred read-only

judge_score

Place a text on an ordered scale you define (lowest level first) and get the nearest level, the exact position and a probability for each level.

Inferred read-only

compare_versions

Which of two versions is stronger for a stated purpose.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.jagent]
url = "https://jev-agent.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "jagent": {
      "type": "http",
      "url": "https://jev-agent.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: jagent
Remote MCP URL: https://jev-agent.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "jagent": {
      "url": "https://jev-agent.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "jagent": {
      "type": "http",
      "url": "https://jev-agent.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "jagent",
  "transport": "streamable-http",
  "url": "https://jev-agent.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.