Reported issues for Agentic SSH

Pod holds 6 of 6 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Agentic SSH.

Most discussed

Feature: Hierarchical Configuration Discovery (Global vs. Project-Specific Overrides)

Problem Statement

As we introduce declarative tool and policy definitions (see #1), the system needs to dynamically scale across different development contexts. Some sensitive, internal repositories might require a heavily locked-down set of allowed commands, while a local home-lab or playground sandbox might want to expand permissions or enter a more relaxed "YOLO mode."

Proposed Solution

Implement a multi-level configuration discovery path at startup that allows project-specific confi

Read the thread · 2026-06-18 · closed · 5 comments

feat: Add configurable connection timeout, SSH ConnectTimeout support, and fail-fast tool execution

Summary

Enhance network resiliency and fail-fast behavior across agentic_ssh connection handling and MCP tool execution.

Motivations & Key Improvements

1. Configurable Connection Timeout:
   • Add connect_timeout_secs in configuration (defaulting to 10s).
   • Support ConnectTimeout directive parsed from ~/.ssh/config.
2. Guarded Network Handshake:
   • Wrap DNS resolution (lookup_host), TCP connection (russh::client::connect), and SSH key/agent authentication in stri

Read the thread · 2026-08-28 · closed · 1 comment

feat: add 'tools' command to list available MCP tools

Problem Statement

Currently, developers interacting with agentic_ssh directly via the CLI or verifying tool definitions must look into the README/documentation or inspect JSON schemas to discover which tools are available and what parameters they expect.

Proposed Solution

Add a top-level CLI command (e.g. agentic_ssh tools / agentic_ssh list-tools) that outputs:

1. Built-in Tools: All default MCP tools provided by agentic_ssh (e.g., list_hosts, run_command, `get_system_s

Read the thread · 2026-08-23 · closed · 1 comment

Documentation and Reference Artifacts for Agent-Friendly Tool Design

Documentation: Add "Agent-Friendly" Guidelines to README and Create agentic_ssh.toml.example

Problem Statement

As we transition to a declarative configuration model using agentic_ssh.toml (see #8), the effectiveness of the exposed MCP tools relies heavily on the text quality of their description fields. Human developers use intuition, but LLM agents parse these strings literally. Poorly written descriptions cause tool drift, execution loops, and hallucinated arguments.

We need to

Read the thread · 2026-06-18 · closed · 1 comment

feat: add 'json' subcommand for direct CLI tool execution]

Implement a CLI subcommand to let developers call MCP tools directly from their shell and return raw JSON outputs.

Read the thread · 2026-07-20 · closed · 0 comments

Implement Host Group Aggregation & Startup Validation

Introduce support for a [groups] table in the configuration file to allow mapping a single logical name to an array of target SSH host aliases. This will enable both AI agents and human operators to target entire infrastructure tiers (e.g., ubuntu, nix, all) in a single query.

Requirements

• Configuration Parsing: Update the configuration parser to read an optional [groups] table mapping group string keys to arrays of host strings.
• Startup Validation: Implement a valid

Read the thread · 2026-07-06 · closed · 0 comments

Most recent

The remaining reports are on the project's issue tracker.