Jagent

Working · 2.4 s

com.jev-agent/jagentv1.0.0 Domain verified

Grade essays, check resumes, and ask typed yes/no, choice and rubric questions, powered by Jev.

Education

Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

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

Authorization (required)

Bearer followed by your Jagent API key (jv_live_...), from https://jev-agent.com/api-access. Listing tools needs no key.

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

check_resume Read-only

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.

resumestring, required

The resume as plain text.

job_descriptionstring

The job posting to match against. Omit for a general resume check.

Tools (7)

check_resume

read-only

Argument	Type	Description
resume*	string	The resume as plain text.
job_description	string	The job posting to match against. Omit for a general resume check.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "resume"
  ],
  "properties": {
    "resume": {
      "type": "string",
      "maxLength": 12000,
      "minLength": 150,
      "description": "The resume as plain text."
    },
    "job_description": {
      "type": "string",
      "maxLength": 8000,
      "description": "The job posting to match against. Omit for a general resume check."
    }
  }
}

compare_versions

Which of two versions is stronger for a stated purpose. Asked twice with the order swapped and averaged, because the model favors the second option on close calls; if the two orders disagree the result is a tie.

read-only

Argument	Type	Description
context	string	The surrounding text, such as the whole essay or the job posting.
question*	string	e.g. 'Which opening line would an admissions reader find more compelling?'
version_a*	string
version_b*	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "question",
    "version_a",
    "version_b"
  ],
  "properties": {
    "context": {
      "type": "string",
      "maxLength": 60000,
      "description": "The surrounding text, such as the whole essay or the job posting."
    },
    "question": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 3,
      "description": "e.g. 'Which opening line would an admissions reader find more compelling?'"
    },
    "version_a": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 1
    },
    "version_b": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 1
    }
  }
}

grade_essay

Grade one essay against a built-in rubric. kind "essay": six criteria and a letter grade, for class essays at middle school, high school or college level. kind "common-app": a Common App personal statement (pass the prompt number, 1-7). kind "sat": an SAT School Day essay, Reading/Analysis/Writing each 1-4 (pass the source passage to check quotations).

read-only

Argument	Type	Description
kind	string
essay*	string	The essay text.
level	string	kind "essay" only. Default high school.
prompt	integer	kind "common-app": which of the seven prompts. Default 7, topic of your choice.
passage	string	kind "sat": the source passage.
assignment	string	kind "essay": the assignment prompt.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "essay"
  ],
  "properties": {
    "kind": {
      "enum": [
        "essay",
        "common-app",
        "sat"
      ],
      "type": "string",
      "default": "essay"
    },
    "essay": {
      "type": "string",
      "maxLength": 20000,
      "minLength": 100,
      "description": "The essay text."
    },
    "level": {
      "enum": [
        "middle school",
        "high school",
        "college"
      ],
      "type": "string",
      "description": "kind \"essay\" only. Default high school."
    },
    "prompt": {
      "type": "integer",
      "maximum": 7,
      "minimum": 1,
      "description": "kind \"common-app\": which of the seven prompts. Default 7, topic of your choice."
    },
    "passage": {
      "type": "string",
      "maxLength": 8000,
      "description": "kind \"sat\": the source passage."
    },
    "assignment": {
      "type": "string",
      "maxLength": 2000,
      "description": "kind \"essay\": the assignment prompt."
    }
  }
}

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. Each submission is graded in its own call, so its score never depends on the others.

read-only

Argument	Type	Description
points	integer
criteria*	array	Rubric rows, e.g. { "name": "Evidence", "description": "Supports the claim with specific evidence" }.
assignment	string
submissions*	array

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "criteria",
    "submissions"
  ],
  "properties": {
    "points": {
      "type": "integer",
      "default": 4,
      "maximum": 6,
      "minimum": 3
    },
    "criteria": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 60,
            "minLength": 1
          },
          "description": {
            "type": "string",
            "maxLength": 300
          }
        }
      },
      "maxItems": 8,
      "minItems": 1,
      "description": "Rubric rows, e.g. { \"name\": \"Evidence\", \"description\": \"Supports the claim with specific evidence\" }."
    },
    "assignment": {
      "type": "string",
      "maxLength": 2000
    },
    "submissions": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "text"
        ],
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 80
          },
          "text": {
            "type": "string",
            "maxLength": 20000,
            "minLength": 100
          }
        }
      },
      "maxItems": 30,
      "minItems": 1
    }
  }
}

judge_choice

Pick the option that best fits a text, with a probability for every option and a confidence. Options map an id to a description of when it applies.

read-only

Argument	Type	Description
text*	string
options*	object	e.g. { "billing": "Payments, refunds, invoices", "technical": "Bugs and errors" }
question*	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "text",
    "question",
    "options"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 60000,
      "minLength": 1
    },
    "options": {
      "type": "object",
      "description": "e.g. { \"billing\": \"Payments, refunds, invoices\", \"technical\": \"Bugs and errors\" }",
      "propertyNames": {
        "type": "string",
        "maxLength": 60,
        "minLength": 1
      },
      "additionalProperties": {
        "type": "string",
        "maxLength": 500,
        "minLength": 1
      }
    },
    "question": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 3
    }
  }
}

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.

read-only

Argument	Type	Description
text*	string
levels*	array	Lowest first, e.g. ["Off-topic", "Partly relevant", "Fully relevant"].
question*	string

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "text",
    "question",
    "levels"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 60000,
      "minLength": 1
    },
    "levels": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 300,
        "minLength": 1
      },
      "maxItems": 10,
      "minItems": 2,
      "description": "Lowest first, e.g. [\"Off-topic\", \"Partly relevant\", \"Fully relevant\"]."
    },
    "question": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 3
    }
  }
}

judge_yes_no

Ask any yes/no question about a text and get the probability that the answer is yes. Use for checks and gates, e.g. 'Does this reply answer the customer's question?'.

read-only

Argument	Type	Description
text*	string	The text to judge.
no_means	string
question*	string
yes_means	string	What a yes looks like, if it helps to spell out.

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "text",
    "question"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 60000,
      "minLength": 1,
      "description": "The text to judge."
    },
    "no_means": {
      "type": "string",
      "maxLength": 300
    },
    "question": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 3
    },
    "yes_means": {
      "type": "string",
      "maxLength": 300,
      "description": "What a yes looks like, if it helps to spell out."
    }
  }
}