Agent SSH MCP (xcdd/Agent-SSH-MCP) is an MCP server listed on the M8ven Trust Index. It scores 35 out of 100, grade F. It declares 14 tools. No publisher has claimed this listing.

F
Warning
35/100

Agent SSH MCP

MCP server for persistent SSH sessions with tmux integration, port forwarding, and SFTP file writes, built for AI agent workflows.

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

xcdd

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — list-hosts (line 256: mkdir(HOSTS_DIR, { recursive: true }))
🚨
Known vulnerabilities in dependencies: 1 critical, 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
// tools this server exposes14 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

add-host

Persist a new SSH host configuration.

list-hosts

List all stored SSH host configurations.

remove-host

Remove a stored SSH host configuration.

edit-host

Edit fields of an existing host configuration.

start-session

Start a new SSH session for a stored host. Automatically initializes tmux if available (user can attach with the tmux session name returned in the response). Falls back to direct shell if tmux is not installed. IMPORTANT: Commands that install tmux itself should be executed BEFORE calling start-sess

exec

Execute a shell command on an existing SSH session. When tmux is active, commands are automatically sent via tmux (non-blocking, user can observe with 'tmux attach -t ai'). IMPORTANT: Just pass the actual command to execute — do NOT manually write 'tmux send-keys' or 'tmux capture-pane', the plugin

close-session

Close an existing persistent SSH session.

upload-file

Upload a local file to the remote server via SFTP. PREFERRED method for writing files — more reliable than echo/cat/heredoc commands, handles binary content and special characters correctly.

download-file

Download a file from the remote server via SFTP.

write-remote-file

Write text content directly to a file on the remote server via SFTP. Preferred over echo/cat/heredoc for writing files — reliable, handles special characters, no shell quoting issues.

setup-tmux

Initialize tmux session on an existing SSH session. Use this after installing tmux on the remote server to switch from direct shell mode to tmux mode. When tmux is active, user can attach with the session name returned by start-session to observe commands in real-time.

forward-port

Create a local TCP port forward through the SSH session. Useful for accessing remote services (e.g. databases) locally. After calling this, connect to 127.0.0.1:<local_port> as if it were <remote_host>:<remote_port> on the server.

stop-forward

Stop a port forward tunnel created by forward-port.

list-sessions

List all active SSH sessions with metadata.

// known CVEs in dependencies1 critical3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.17.5GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.17.5GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.17.5GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configALL_PROXY
configHTTPS_PROXY
configHTTP_PROXY
configSSH_AUTH_SOCKAuthentication priority: password → private key → SSH agent ().
configall_proxy
confighttp_proxy
confighttps_proxy
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

14/14 tools missing one or more hints — add-host (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list-hosts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); remove-host (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — list-hosts (line 256: mkdir(HOSTS_DIR, { recursive: true }))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool test coverage

Only 0/14 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.17.5 (high), @modelcontextprotocol/sdk@1.17.5 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Tool description accuracy

list-hosts: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/xcdd/agent-ssh-mcp?variant=verified)](https://m8ven.ai/mcp/xcdd/agent-ssh-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 2e9794d95bb400b916533895fd9b61ce356215a5
code hash: d1426d55241a0b91c446e844a93b444587df0cb0f85b5012db44e56b32ef7bca
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client