Remote Agents vs SSH MCP Server

A side-by-side look at the Remote Agents and SSH MCP Server MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Remote Agents logoRemote AgentsCommand Line · Local subprocess (stdio)Control fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce.56GoodAuth: not declaredSSH MCP Server logoSSH MCP ServerCommand Line · Local subprocess (stdio)MCP server for SSH operations with built-in diagnostics64GoodAuth: not declared

Verdict: choose Remote Agents for command line work as a local process; choose SSH MCP Server for command line as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Remote Agents logoChoose Remote Agents when

  • You need dedicated capabilities in the Command Line domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like exec, read_file, get_info.
Explore Remote Agents

SSH MCP Server logoChoose SSH MCP Server when

  • You need dedicated capabilities in the Command Line domain.
  • You prefer a local stdio subprocess transport.
  • You want tools like ssh_exec, ssh_read_file, ssh_write_file.
Explore SSH MCP Server

Feature & specification comparison

Rows where the two servers differ are marked.

SpecRemote Agents logoRemote AgentsSSH MCP Server logoSSH MCP Server
CategoryCommand LineCommand Line
Quality signal56/100 · Good64/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars16
Directory activity 1 views 0 installs 0 upvotes 4 views 0 installs 0 upvotes
Tools1521

Tools & capabilities

Remote Agents tools 15

  • execRun a shell command (locally or on a remote agent via `agent_id`)
  • read_fileFile operations (write requires Edit/Bypass)
  • get_infoInspect / change an agent's mode at runtime
  • git_statusGit operations
  • schedule_addCron-style tasks on a host
  • task_dispatchAutonomous AI tasks run with the host's own credentials
  • session_listBrowse the host's AI-chat history (claude / opencode / codex / cline / roo / kilo / zed / cursor / gemini / qwen / goose / continue); `session_get` fetches a transcript or a window around one message
  • session_searchFull-text search over the host's AI-chat history — a local Tantivy (BM25) index of every provider transcript, returning ranked cited snippets with `session_id` + message position (follow up with `session_get { around_seq }` for the context)
  • list_agentsList agents connected to the relay room
  • fleet_execRun an operation across the fleet — `target = all \
  • fleet_session_searchSearch the AI-chat history across the whole fleet: every matched host queries its local index, hits merge by score with host labels
  • file_searchFind files on a host, and move a file host→host (UDP, SHA-256 verified)
  • +3 more on the listing page

SSH MCP Server tools 21

  • ssh_execExecute a command on a remote host via SSH. The command is interpreted by the remote login shell — pipes, redirects, globs, and other shell metacharacters work as expected. Returns up to three content blocks in this order: the status (`[exit code: N]`, plus the signal and any truncation), then `[stderr]`, then `[stdout]`. Status comes first so a proxy that cuts long results (Yaw MCP keeps about 100 KB) never drops the exit code; for big output, filter or page on the remote (head, tail, grep). Use `env` to set environment variables for this call without modifying the command string. Subject to SSH_MCP_COMMAND_WHITELIST / SSH_MCP_COMMAND_BLACKLIST if configured (policy is checked against the env-prefixed command).
  • ssh_read_fileRead a file from a remote host via SFTP. A whole-file read is limited to 10 MB. For a large file -- or behind a proxy that caps results, such as Yaw MCP at about 100 KB -- read it in pages with `offset` and `length` (bytes): a paged read returns a status block first (`[bytes A-B of SIZE]` and the next offset) and then the text. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting.
  • ssh_write_fileWrite content to a file on a remote host via SFTP. Creates or overwrites the file. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting. NOT gated by SSH_MCP_COMMAND_WHITELIST / SSH_MCP_COMMAND_BLACKLIST: command policy applies only to ssh_exec and ssh_multi_exec, so a blacklist such as `^rm` does NOT block this tool.
  • ssh_uploadUpload a local file to a remote host via SFTP. Reads an arbitrary local file at an agent-chosen `localPath` -- any file readable by this process leaves the machine toward the remote host (the mirror direction of ssh_download's local write). If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting. NOT gated by SSH_MCP_COMMAND_WHITELIST / SSH_MCP_COMMAND_BLACKLIST: command policy applies only to ssh_exec and ssh_multi_exec, so a blacklist such as `^rm` does NOT block this tool.
  • ssh_downloadDownload a file from a remote host to local filesystem via SFTP. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting.
  • ssh_lsList files in a directory on a remote host via SFTP. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting.
  • ssh_statGet metadata for a file or directory on a remote host via SFTP. Returns size, permissions (octal), uid/gid, mtime/atime, and the path type. Symlinks are reported as `symlink -> <target kind>`: the type describes the link itself while size/mode/mtime describe its TARGET, and a dangling symlink is reported rather than erroring. Use this instead of parsing `ls -la` output. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting.
  • ssh_mkdirCreate a directory on a remote host via SFTP. Set `recursive: true` to create parent directories as needed (like `mkdir -p`). Existing intermediate dirs are tolerated; an existing leaf path is still an error. Unlike the other SFTP tools, the path may be relative. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting. NOT gated by SSH_MCP_COMMAND_WHITELIST / SSH_MCP_COMMAND_BLACKLIST: command policy applies only to ssh_exec and ssh_multi_exec, so a blacklist such as `^rm` does NOT block this tool.
  • ssh_deleteDelete a file or empty directory on a remote host via SFTP. Auto-detects the path type and calls the right SFTP op (unlink for files/symlinks, rmdir for empty dirs). Recursive directory delete is intentionally NOT supported -- for that, use ssh_exec with `rm -rf` explicitly so the destructive intent is visible in the tool trace. If the connection pool is full (SSH_MCP_MAX_POOL_SIZE, default 100), waits up to 30s for a free slot before starting. NOT gated by SSH_MCP_COMMAND_WHITELIST / SSH_MCP_COMMAND_BLACKLIST: command policy applies only to ssh_exec and ssh_multi_exec, so a blacklist such as `^rm` does NOT block this tool.
  • ssh_diagnoseDiagnose SSH connectivity issues. Checks ssh-agent status, loaded keys, known_hosts, SSH config, and attempts a test connection. Use this BEFORE attempting SSH operations if you suspect connectivity issues, or AFTER a failed SSH operation to understand why it failed.
  • ssh_agent_ensureEnsure ssh-agent is running and reachable. Starts a new agent if needed and sets environment variables so subsequent SSH operations work. Use this FIRST when SSH operations fail with agent-related errors.
  • ssh_key_listList all SSH private keys in ~/.ssh/ with their type, fingerprint, and whether they are loaded in the agent. Use this to find which keys are available and which ones need to be loaded. Reports isError only when ~/.ssh exists but could not be read -- an absent or empty ~/.ssh is a successful answer with a ssh-keygen hint.
  • +9 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Remote Agents

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "remote-agents": {
      "command": "npx",
      "args": [
        "-y",
        "remote-agents"
      ]
    }
  }
}

SSH MCP Server

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "ssh-mcp-server-2": {
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/ssh-mcp"
      ]
    }
  }
}

Frequently asked questions

Remote Agents is categorized under Command Line and uses a local stdio subprocess. SSH MCP Server belongs to Command Line and uses a local stdio subprocess. Pick Remote Agents for command line work and SSH MCP Server for command line.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Remote Agents has no declared pricing — check the project's own site. SSH MCP Server has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add remote-agents and ssh-mcp-server-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Remote Agents has a quality signal of 56/100 (Good) with 1 views, 0 installs and 1 GitHub stars. SSH MCP Server has 64/100 (Good) with 4 views, 0 installs and 6 GitHub stars.