MCP SSH Session

by AmritaBot

Overview Schema Source Related Servers Discussions Admin

Python

Remote

read_file

Read a remote file over SSH. Falls back to sudo cat if permission denied.

Instructions

Read a remote file over SSH. Falls back to sudo cat if permission denied.

Returns at most max_bytes bytes, cut on a character (and line) boundary. A truncated result reports the line range and how to resume with start_line or offset.

Input Schema

Name	Required	Default
`host`	Yes
`port`	No
`errors`	No	replace
`offset`	No
`encoding`	No	utf-8
`password`	No
`use_sudo`	No
`username`	No
`max_bytes`	No
`start_line`	No
`remote_path`	Yes
`key_filename`	No
`sudo_password`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.4.2Oct 14, 2026
- addedInput schema / properties / offset
```
Added value: +{
+  "default": 0,
+  "type": "integer"
+}
```
- addedInput schema / properties / start_line
```
Added value: +{
+  "default": 1,
+  "type": "integer"
+}
```
First observedv0.2.1Jul 20, 2026

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It helpfully discloses the sudo-cat fallback on permission denial and the character/line-boundary truncation plus resume mechanics (start_line/offset), which is genuine value. However, with 13 parameters including password, key_filename, username, and sudo_password, it says nothing about authentication requirements or privilege escalation, leaving a material gap.

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 core action and followed by the two behaviors that matter most (fallback and truncation). No filler, no repetition of what the schema already shows.

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

Completeness2/5

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

An output schema exists so return values need not be explained, but for a 13-parameter SSH tool with zero annotation and zero schema-description coverage, the description omits authentication setup, privilege handling, and most parameter meanings. It is adequate for the truncation story but incomplete overall.

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

Parameters2/5

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

Schema description coverage is 0% across 13 parameters, so the description must compensate and largely does not. It adds real meaning for max_bytes, start_line, and offset (truncation and resume semantics), but the remaining ten parameters—host, port, credentials, encoding, errors, use_sudo—receive no explanation whatsoever.

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 names a specific verb and resource ("Read a remote file over SSH"), which clearly separates it from the write_file sibling by verb alone. It stops short of explicitly naming or contrasting with alternatives, so it earns a 4 rather than a 5.

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 guidance on when to use this tool versus siblings like execute_command (e.g. a shell cat) or read_screen. The fallback mention (sudo cat) describes internal behavior, not a decision rule for the agent, so usage remains implied at best.

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