ssh-session-mcp
SSH Session MCP fills a gap in the MCP ecosystem by offering a persistent shared SSH PTY runtime, not just stateless command execution. It features browser collaboration, input locking, safe/full execution modes, async command tracking, configurable policy rules, and multi-device profiles. Ideal for remote development, embedded systems, infrastructure workflows, and hardware control scenarios.
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
Zw-awa
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.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
ws: Uninitialized memory disclosure
AUTO_OPEN_TERMINALdefaults to false in the container because browser auto-open from inside a container is usually not useful.DEVICE_A_PASSWORD"auth": { "passwordEnv": "" },SSH_HOSTYOUR_DEVICE_HOSTSSH_KEYLocal private key path emptySSH_KEY_FILEFile containing the SSH private key emptySSH_MCP_AUTH_MODEoff or proxy offSSH_MCP_AUTH_ROLE_HEADERAuthenticated role header name x-ssh-session-mcp-roleSSH_MCP_AUTH_USER_HEADERAuthenticated user header name x-ssh-session-mcp-userSSH_MCP_CONFIGe =/workspace/ssh-session-mcp.config.json \SSH_MCP_DEBUGEnable debug browser actions falseSSH_MCP_DISABLE_MAINSSH_MCP_INSTANCERuntime isolation key proc-<pid> or helper-selectedSSH_MCP_LOCALLaunch a local shell instead of SSH falseSSH_MCP_LOG_DIRMetadata log directory platform defaultSSH_MCP_LOG_MODEoff, meta, or stderr logging offSSH_MCP_MODEsafe or full safeSSH_MCP_NODE_IDStable logical node id for this replica runtime instance idSSH_MCP_PUBLIC_BASE_URLPublic viewer base URL advertised to other replicas unsetSSH_MCP_REDIS_URLRedis connection URL required when SSH_MCP_STORE=redisSSH_MCP_RUNTIME_MODEsingle-node or distributed single-nodeSSH_MCP_STATE_DIRRuntime state root directory platform defaultSSH_MCP_STOREDistributed v0 requires Redis for real multi-node deployments. =memory only exists for local skeleton testing and does not provide a shared store across replicas.SSH_MCP_TRUST_PROXYWhether to trust authenticated proxy headers falseSSH_MCP_USE_MARKERSSH_PASSWORDPassword auth emptySSH_PASSWORD_FILEFile containing the SSH password emptySSH_PORTLegacy single-target SSH port 22SSH_USERYOUR_DEVICE_USERVIEWER_HOSTe =0.0.0.0 \VIEWER_LAUNCH_MODEVIEWER_PORTThe image defaults to 8793 when unset so the browser viewer can be published reliably.XDG_CONFIG_HOMEXDG_STATE_HOMETool 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
23/23 tools missing one or more hints — ssh-session-open (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ssh-session-send (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ssh-device-list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +20 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.
Tool inputs are validated
20/23 tool handlers declare input schemas (87%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 4/23 tool handlers wrap calls in try/catch (17%)
Wrap each tool handler body in try/catch and return a structured error response.
Tool test coverage
Only 6/23 tools referenced in tests (26%)
Write tests that reference each tool by name so every tool has at least one test.
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, 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.
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/zw-awa/ssh-session-mcp)?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