Defense MCP
This is a Linux OS hardening tool. Take a fresh install and immediately harden the heck out of it using just your favourite LLM agent and natural language prompts. "Make my system secure" or "Do a full security audit of my system."
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
bottobot
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
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.
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
DEFENSE_MCP_ALLOWED_DIRS"": "/tmp,/home,/var/log"DEFENSE_MCP_ALLOWED_TOOLSDEFENSE_MCP_AUTO_INSTALLfalse node build/index.jsDEFENSE_MCP_BACKUP_DIRDEFENSE_MCP_BACKUP_ENABLEDtrue Auto-backup before system changesDEFENSE_MCP_CHANGELOG_PATHDEFENSE_MCP_COMMAND_TIMEOUTDEFENSE_MCP_DRY_RUN"": "true",DEFENSE_MCP_LOG_FILEDEFENSE_MCP_LOG_LEVELinfo Log verbosity (debug/info/warn/error)DEFENSE_MCP_LOG_MAX_FILESDEFENSE_MCP_LOG_MAX_SIZEDEFENSE_MCP_MAX_OUTPUT_SIZEDEFENSE_MCP_NETWORK_TIMEOUTDEFENSE_MCP_POLICY_DIRDEFENSE_MCP_PREFLIGHTtrue Enable pre-flight dependency checksDEFENSE_MCP_PREFLIGHT_BANNERStrue Show pre-flight status in tool outputDEFENSE_MCP_PROTECTED_PATHSDEFENSE_MCP_QUARANTINE_DIRDEFENSE_MCP_RATE_LIMIT_GLOBALDEFENSE_MCP_RATE_LIMIT_PER_TOOLDEFENSE_MCP_RATE_LIMIT_WINDOWDEFENSE_MCP_READ_ONLYDEFENSE_MCP_REDACT_OUTPUTDEFENSE_MCP_REQUIRE_CONFIRMATIONtrue Require confirmation for destructive actionsDEFENSE_MCP_RUNTIME_PATH_VERIFYDEFENSE_MCP_SUDO_TIMEOUTDEFENSE_MCP_THIRD_PARTY_INSTALLRequires explicit =true to enableDEFENSE_MCP_TIMEOUT_DEFAULTDEFENSE_MCP_TIMEOUT_LYNISDEFENSE_MCP_TIMEOUT_NMAPDISPLAYLOGNAMEMCP_API_KEYMCP_PORT3100 HTTP server port (when MCP_TRANSPORT=http)MCP_TRANSPORTstdio Transport mode: stdio or httpSSH_CONNECTIONSSH_TTYSUDO_ASKPASSWAYLAND_DISPLAYTool 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
40/40 tools missing one or more hints — access_control (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); api_security (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); app_harden (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +37 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.
Destructive tools are labelled
4 tools perform destructive updates without destructiveHint — access_control deletes at line 1943 (unlinkSync(tempPath)); honeypot_manage deletes at line 572 (rmSync(canary.path, { recursive: true, force: true })); malware deletes at line 563 (fs.rmdirSync(restoreDir))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — dns_security (line 203: dnsQueryRe.exec(line)); sudo_session (line 909: fs.writeFileSync(scriptPath, scriptLines.join("\n") + "\n", { mode: 0o700 }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
19/31 tool handlers declare input schemas (61%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
12/40 tools referenced in tests (30%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
17 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Tool description accuracy
3 tools have description/behavior mismatches: dns_security: description implies read-only but handler writes/deletes/executes; ebpf: description implies read-only but handler writes/deletes/executes; sudo_session: 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.
[](https://m8ven.ai/mcp/bottobot/defense-mcp-server)?variant=verified to the badge 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