qnx-mcp

Overview Schema Source Related Servers Discussions Admin

Copy a file from a QNX target

file_get

Copies a regular file from a QNX target to the build host, verifies size and SHA-256, and returns small UTF-8 files inline when possible.

Instructions

Copy one regular file from the target to the build host, verifying size and SHA-256. Without local_path it lands in the server's state directory (path returned); with local_path it never follows or replaces a symlink and replaces a file only with overwrite=true. UTF-8 files up to 64 KiB are also returned inline as text.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target": "<target>",
      "remote_path": "<remote_path>"
    },
    "name": "file_get"
  }
}

Input Schema

Name	Required	Description
`max_mb`	No
`target`	Yes	Target name such as 'tb' (lowercase letters, digits, '-', '_'); must be inside the server allowlist
`overwrite`	No
`local_path`	No	Host destination (absolute); default: a new file in the server state dir
`remote_path`	Yes	Absolute path of the file on the target

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: size and SHA-256 verification, a strict no-symlink-follow/no-symlink-replace guarantee, conditional replacement gated on overwrite, and inline text return for UTF-8 files up to 64 KiB. These are exactly the mutation-safety and side-effect facts an agent cannot derive from readOnlyHint=false / destructiveHint=false / idempotentHint=false.

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?

Three tight sentences, front-loaded with the verb and verification guarantee, then the destination modes, then the inline-text special case. No filler and no restatement of the name or title.

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?

An output schema exists, so the return path and inline text need not be explained further, and the description still flags that a path is returned. The remaining gap is the size cap behavior (max_mb) — whether exceeding it errors out — which matters for a copy tool with a 16 MB default.

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?

At 60% schema coverage the description carries real weight: it defines local_path's default destination and overwrite's effect precisely, and confirms the single-file scope. The one gap is max_mb, which is undocumented in both the schema and the description despite bounding what can be copied (default 16 MB, max 1024).

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

Purpose5/5

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

States a specific verb and resource ('Copy one regular file from the target to the build host') plus a scope qualifier that rules out directories and multi-file copies. The direction (target -> host) implicitly but clearly separates it from the inverse sibling file_put.

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?

Explains the two operating modes concretely: without local_path it lands in the server state dir, with local_path it writes to that host path and requires overwrite=true to replace an existing file. It does not name an alternative tool or say when to prefer file_list/file_put, so it falls short of an explicit when/when-not routing statement.

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