jev

Overview Schema Source Related Servers Discussions Admin

Search a directory by meaning

jev_search

Read-onlyIdempotent

Search a directory to answer questions, ranking ripgrep matches with neighboring lines to return the most relevant hits with paths and line numbers.

Instructions

Find the lines across a whole directory that answer a question, instead of reading pages of grep hits. The server runs ripgrep (honouring .gitignore and .ignore, skipping hidden, binary and credential files), keeps lines matching an optional regex 'pattern' as candidates, and Jev ranks them with their neighbouring lines. Returns path, line number and the line's text for the best hits, per question. Use a broad pattern to narrow cheaply (e.g. 'retr|backoff'), then let Jev judge meaning. Without a pattern every non-empty line is a candidate, so also set include or a small dir. Pass every question you have about this area in one call, with a pattern covering all of them: the candidates are read once for all questions.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dir`	No	Directory to search, below an allowed root. Relative paths resolve against the first root.	.
`top`	No	How many hits to return per question.
`context`	No	Neighbouring lines sent with each candidate, on each side.
`include`	No	Only files whose name ends with one of these, e.g. ['.ts', '.md'].
`pattern`	No	ripgrep (Rust) regex a line must match to be a candidate. No lookaround or backreferences.
`questions`	Yes	Every question you have about this text, each stated in full (up to 16). They are judged in one pass over the same text, so extra questions cost almost nothing: batch them rather than calling again. Questions cannot see each other's answers.
`ignore_case`	No	Match pattern case-insensitively.
`no_at_or_below`	No	Probability at or below which a check's verdict is 'no'. Default 0.3. Between the two the verdict is 'uncertain'.
`yes_at_or_above`	No	Probability at or above which a check's verdict is 'yes'. Default 0.7.

Output Schema

TableJSON Schema

Name	Required	Description
`model`	Yes
`usage`	Yes
`results`	Yes	One per question, in the order asked.
`windows`	Yes
`candidates`	Yes	Lines judged.
`latency_ms`	Yes	Wall-clock milliseconds for the API round trip, for your own calibration logs.
`thresholds`	Yes
`files_matched`	Yes	Files with at least one candidate line.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.14.0Sep 25, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool read-only and non-destructive, and the description adds meaningful behavioral detail: ripgrep honors .gitignore/.ignore, skips hidden/binary/credential files, optional regex filtering, neighboring-line ranking, and the no-pattern fallback to every non-empty line. This goes well beyond the structured hints without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well organized: purpose first, then mechanism, return value, and practical tips. Every sentence adds operational information, and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter tool with an output schema and strong annotations, the description covers the important caveats (gitignore handling, credential-file skipping, no-pattern behavior, one-pass batching) that an agent needs before calling. The schema handles the remaining parameter details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds value by explaining how 'pattern' should be used broadly, what happens without it, and why 'questions' should be batched. It does not comment on every parameter, but the schema already documents those.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds lines across a directory that answer a question and ranks them by meaning, with a specific return shape (path, line number, text). It distinguishes from grep but does not explicitly differentiate from sibling Jev tools such as jev_locate or jev_ask.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete usage guidance: use a broad regex pattern to narrow candidates cheaply, set include or use a small dir when no pattern is given, and batch all questions into one call since candidates are read once. It does not explicitly state when to prefer a sibling tool, so it stops short of full when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server