ssh-mcp-server-secured (marian-craciunescu/ssh-mcp-server-secured) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.
A secured MCP server for safe remote server management via SSH with command filtering, network device support, and bulk connection management.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
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
marian-craciunescu
Source: Glama
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
MCP_PORTSSE_PORTSSH_ALLOW_SUDOtrue, false true Allow sudo commandsSSH_AUDIT_DIRpath ./audit Directory for daily audit_YYYY-MM-DD.jsonl filesSSH_AUDIT_ENABLEDtrue, false true Write a per-command session audit (command + full output) to JSONLSSH_BLACKLISTcomma-separated or JSON - Override blacklist commandsSSH_DISABLE_PAGERPROFILE_<NAME>_DISABLE_PAGER=false turns off pager suppression for connections using that profile, overriding the global default.SSH_ENABLE_LARGE_OUTPUTtrue, false false Offload oversized command output to an upload endpoint and return a URI instead of inline textSSH_FAILED_CONNECTIONS_LOGfile path ./ssh-failed-connections.json /var/log/ssh-failed.jsonlSSH_FILE_UPLOAD_ENDPOINTURL - POST target for large output. Receives {content, filename}, must return {file_id, artifact_uri}SSH_FILTER_MODE"": "blacklist",SSH_HOST_BLACKLISTcomma-separated IPs - Blacklist of allowed host IPsSSH_HOST_FILTER_MODEwhitelist, blacklist, disabled disabled Host filtering modeSSH_HOST_WHITELISTcomma-separated IPs - Whitelist of allowed host IPsSSH_IDLE_TIMEOUTseconds 120 Idle connection timeoutSSH_LOG_BLOCKEDtrue, false true Log blocked commands to stderrSSH_LOG_FILEPath to log file (none)SSH_LOG_LEVELDEBUG, INFO, WARN, ERROR INFOSSH_MAX_OUTPUT_LENGTHinteger (chars) 10000 Output size threshold above which output is offloadedSSH_MAX_PAGER_PAGESinteger 1000 Safety cap on auto-paged pages per commandSSH_MCP_CONFIGfile path - Path to config JSON fileSSH_PAGER_ADVANCE_KEYstring " " (space) Key sent to advance to the next pager pageSSH_PAGER_REGEXregex string built-in Override the pattern used to detect a pager promptSSH_WHITELISTcomma-separated or JSON - Override whitelist commandsTool 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
13/13 tools missing one or more hints — ssh_connect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ssh_connect_with_jump_command (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ssh_load_connections (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 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.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.25.0 (high), @modelcontextprotocol/sdk@1.25.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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.
[](https://m8ven.ai/mcp/marian-craciunescu-ssh-mcp-server-secured-6xgnty)?variant=verified from the URL.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