Skip to main content
Glama
remote-ssh-mcp
by RuiFG

ssh_download_file

Destructive

Download a remote file over SFTP to an exact local path, with overwrite disabled by default.

Instructions

Stream one remote file to an exact local path via SFTP. Local paths are relative to the MCP server startup directory. Transfers directly without a confirmation dialog. overwrite defaults to false.

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": {
      "hostId": "<hostId>",
      "remotePath": "<remotePath>",
      "localPath": "<localPath>"
    },
    "name": "ssh_download_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostIdYesRequired stable host ID returned by ssh_list_hosts. Names are not accepted.
localPathYes
overwriteNo
remotePathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false, idempotentHint=false), the description adds two genuinely useful behavioral facts: transfers happen without a confirmation dialog, and local paths resolve against the server startup directory rather than the agent's cwd. It still omits what happens when the target exists and overwrite is false, and whether parent directories are created.

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?

Four short declarative sentences, front-loaded with the core action and followed by the two constraints an agent most needs before calling. No filler, no restatement of the tool name.

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

Completeness3/5

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

For a destructive local-disk write with no output schema, the definition should say what the call returns (bytes written? local path?) and what error surfaces when overwrite is false and the file exists. It covers path resolution and confirmation behavior well, but the collision and return-value story is missing.

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 only 25% — hostId is documented, remotePath and localPath and overwrite are not. The description compensates partially by defining localPath's resolution base and restating overwrite's default, but remotePath gets no semantics at all (single file only? symlinks? glob rejection?) and the overwrite=false failure mode is undefined.

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 — stream one remote file to an exact local path via SFTP — so the agent knows this is a download, not a read-into-context operation. It never names ssh_read_file or ssh_upload_file, so the boundary with the read sibling is left implicit, but the destination-path framing does the distinguishing work.

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 'exact local path' and 'relative to the MCP server startup directory' wording implies you use this when you need a persistent local copy rather than file contents, but there is no explicit when-to-use versus ssh_read_file, and no stated preconditions such as the host needing a passing ssh_test_connection. Usage is inferable, not instructed.

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