bash-mcp

Overview Schema Source Related Servers Discussions Admin

Find files

find_files

Read-only

Locate files by name pattern, type, or modification time and return a structured path list; combine multiple glob patterns with OR logic or filter to recently modified files.

Instructions

Find files by name pattern, type, or modification time. Returns structured list of paths. Use names for multiple glob patterns (OR logic), modifiedWithin for recent files (e.g. '7d', '1h').

Input Schema

Name	Required	Description	Default
`name`	No	Filename glob pattern (e.g. '*.ts')
`path`	No	Root directory to search (default: '.')	.
`type`	No	Filter by type
`names`	No	Multiple filename glob patterns (e.g. ['.ts', '.py', '*.sh']). Combined with OR logic.
`pattern`	No	Alias for name — filename glob pattern (e.g. '*.ts')
`maxDepth`	No	Max search depth
`withMetadata`	No	Include size (bytes) and mtime (unix timestamp) for each file
`modifiedWithin`	No	Modified within timespan (e.g. '7d', '1h')

Output Schema

Name	Required	Description	Default
`count`	Yes
`files`	Yes
`metadata`	No
`retained`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv5.0.1Oct 23, 2026

TDQS

A3.5/5.0

Behavior3/5

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

readOnlyHint=true already establishes this is a safe non-mutating search, so the description's burden is lower. It adds the return shape ('structured list of paths') and the OR semantics, but says nothing about recursion depth behavior, symlink handling, result volume/limits, or ordering — the traits an agent would actually want before running a broad search.

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

Conciseness4/5

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

Three tight sentences with the core purpose front-loaded and no filler. The 'Returns structured list of paths' clause is mildly redundant given an output schema exists, which keeps it just short of a 5.

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

Completeness4/5

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

Structural burden is low: all 8 parameters are optional, the schema is fully documented, and an output schema covers return values. The only real gap is the unexplained name/pattern alias overlap, which an agent could stumble on; otherwise the definition is sufficient to invoke the tool correctly.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description merely restates what the schema already says ('names' OR logic appears verbatim in the schema description), and it does not resolve the genuinely ambiguous case of three overlapping filters — name, names, and pattern (an alias) — leaving the agent without guidance on which to use.

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?

States a specific verb and resource (find files) plus the three filtering axes (name pattern, type, modification time) and the return shape (list of paths). It does not differentiate from overlapping siblings such as glob, ls, or tree, so an agent can't tell on purpose alone which one to prefer.

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

Usage Guidelines3/5

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

The second sentence gives real selection guidance between parameters ('names' for multiple globs with OR logic, 'modifiedWithin' for recent files), which is useful. But there is no when-to-use-this-vs-alternatives guidance, and the sibling set contains glob and ls that an agent would reasonably confuse with this tool.

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

Deploy Server