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

ssh_upload_file

Destructive

Upload a local file, including binary data, to an exact remote path over SFTP using a host ID; set overwrite to replace an existing file.

Instructions

Stream one local file, including binary data, to an exact remote 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>",
      "localPath": "<localPath>",
      "remotePath": "<remotePath>"
    },
    "name": "ssh_upload_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

B3.2/5.0
Behavior3/5

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

This adds real context beyond the annotations: transfers directly without a confirmation dialog (critical given destructiveHint=true), overwrite defaults false, and binary data is supported. It still does not say what happens on failure or partial transfer, or what the result contains.

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?

Four short sentences, front-loaded with the core action and protocol. The overwrite sentence partly restates the schema default but is defensible as a safety emphasis.

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?

Adequate for a mutation tool with no output schema and a 4-param surface: it covers the safety posture, path resolution, and binary support. It is missing outcome behavior (what a successful return looks like, error cases) which matters for a destructive, non-idempotent transfer.

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 25% (only hostId documented), so the description usefully clarifies that localPath is relative to the MCP server startup directory and that remotePath must be exact. However, it does not explain overwrite=true behavior, path separator conventions, or directory creation, leaving half the gap.

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 local file (including binary data) to an exact remote path via SFTP. That is clear and distinguishes it from a line-oriented writer like ssh_write_file, though it never names that sibling to confirm the boundary.

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

Usage Guidelines2/5

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

There is no when-to-use guidance. The description never says when to prefer this over ssh_write_file or how it differs from uploads of text data, and offers no prerequisites such as whether the remote directory must already exist.

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