Defense MCP (bottobot/defense-mcp-server) is an MCP server listed on the M8ven Trust Index. M8ven graded this before, but the code is no longer public at the location we read it, so we cannot re-check it. No publisher has claimed this listing.

—

Source no longer public

Defense MCP

Item: Defense MCP
Author: M8ven

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."

→ bottobot/defense-mcp-server · listed on glama

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 push why connect →

Who stands behind it

bottobot

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 →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

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

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 }))

🚨

Known vulnerabilities in dependencies: 1 critical

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 1 credential: MCP_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes36 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.

access_control

Access control: SSH, PAM, sudo, user audit, password policy, shell restriction

api_security

API security: local API discovery, auth audit, rate limiting, TLS verify, CORS check

app_harden

App hardening: audit running apps, recommendations, firewall rules, systemd sandboxing

backup

Backup: config files, system state snapshots, restore, verify integrity, list backups

cloud_security

Cloud: environment detection, metadata audit, IAM credentials, storage audit, IMDS security

compliance

Compliance: Lynis, OpenSCAP, CIS benchmarks, framework checks, policy, cron/tmp hardening

container_docker

Docker security: audit, CIS bench, seccomp, daemon config, image scan

container_isolation

Container isolation: AppArmor, SELinux, namespaces, seccomp, rootless setup

honeypot_manage

Deception: canary tokens, honeyport listeners, trigger detection, canary management

dns_security

DNS: resolver audit, DNSSEC check, tunneling detection, domain blocklists, query log audit

ebpf

eBPF/Falco: list eBPF programs, Falco status, deploy rules, read events

crypto

Crypto: TLS/SSL audit, GPG, LUKS, file hashing, certificate lifecycle

firewall

Firewall: iptables, UFW, nftables, persistence, policy audit

harden_kernel

Kernel hardening: sysctl, kernel security, bootloader, memory protections

harden_host

Host hardening: services, permissions, systemd, cron, umask, banners, USB control

incident_response

Incident response: volatile data, IOC scan, timeline, forensics (memory/disk/network/evidence/custody)

integrity

Integrity: AIDE, rootkit scanning, file hashing, drift baselines

log_management

Logging: auditd, journalctl, fail2ban, syslog, log rotation, SIEM integration

malware

Malware: ClamAV scan/update, YARA rules, suspicious files, webshells, quarantine

defense_mgmt

Defense: tool checks, workflows, change history, posture, scheduled audits, remediation, reports

network_defense

Network: connections, traffic capture, port scan detection, IPv6 audit, self-scan, segmentation

patch

Patches: pending updates, unattended upgrades, package integrity, kernel audit, CVE lookup

process_security

Processes: audit running, capabilities, namespaces, anomaly detection, cgroup limits

secrets

Secrets: filesystem scan, env variable audit, SSH key sprawl, git history leak detection

sudo_session

Sudo: elevate privileges, check/drop/extend session, preflight tool checks

supply_chain

Supply chain: SBOM generation, cosign artifact signing, SLSA provenance verification

threat_intel

Threat intel: IP/hash/domain reputation, feed management, blocklist application

vuln_manage

Vulnerabilities: nmap scan, nikto web scan, tracking, risk prioritization, remediation plans

waf_manage

WAF: ModSecurity audit, rule management, rate limiting, OWASP CRS, blocked request analysis

wireless_security

Wireless: Bluetooth audit, WiFi assessment, rogue AP detection, disable unused interfaces

zero_trust

Zero-trust: WireGuard VPN, peer management, mTLS certificates, microsegmentation

my_custom_tool

firewall_iptables

test_tool

log_auditd

single_arg

// known CVEs in dependencies1 critical

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

criticalvitest@4.0.18GHSA-5xrq-8626-4rwp

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

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.

configDEFENSE_MCP_ALLOWED_DIRS"": "/tmp,/home,/var/log"

configDEFENSE_MCP_ALLOWED_TOOLS

configDEFENSE_MCP_AUTO_INSTALLfalse node build/index.js

configDEFENSE_MCP_BACKUP_DIR

configDEFENSE_MCP_BACKUP_ENABLEDtrue Auto-backup before system changes

configDEFENSE_MCP_CHANGELOG_PATH

configDEFENSE_MCP_COMMAND_TIMEOUT

configDEFENSE_MCP_DRY_RUN"": "true",

configDEFENSE_MCP_LOG_FILE

configDEFENSE_MCP_LOG_LEVELinfo Log verbosity (debug/info/warn/error)

configDEFENSE_MCP_LOG_MAX_FILES

configDEFENSE_MCP_LOG_MAX_SIZE

configDEFENSE_MCP_MAX_OUTPUT_SIZE

configDEFENSE_MCP_NETWORK_TIMEOUT

configDEFENSE_MCP_POLICY_DIR

configDEFENSE_MCP_PREFLIGHTtrue Enable pre-flight dependency checks

configDEFENSE_MCP_PREFLIGHT_BANNERStrue Show pre-flight status in tool output

configDEFENSE_MCP_PROTECTED_PATHS

configDEFENSE_MCP_QUARANTINE_DIR

configDEFENSE_MCP_RATE_LIMIT_GLOBAL

configDEFENSE_MCP_RATE_LIMIT_PER_TOOL

configDEFENSE_MCP_RATE_LIMIT_WINDOW

configDEFENSE_MCP_READ_ONLY

configDEFENSE_MCP_REDACT_OUTPUT

configDEFENSE_MCP_REQUIRE_CONFIRMATIONtrue Require confirmation for destructive actions

configDEFENSE_MCP_RUNTIME_PATH_VERIFY

configDEFENSE_MCP_SUDO_TIMEOUT

configDEFENSE_MCP_THIRD_PARTY_INSTALLRequires explicit =true to enable

configDEFENSE_MCP_TIMEOUT_DEFAULT

configDEFENSE_MCP_TIMEOUT_LYNIS

configDEFENSE_MCP_TIMEOUT_NMAP

configDISPLAY

configLOGNAME

🔐 secretMCP_API_KEY

configMCP_PORT3100 HTTP server port (when MCP_TRANSPORT=http)

configMCP_TRANSPORTstdio Transport mode: stdio or http

configSSH_CONNECTION

configSSH_TTY

configSUDO_ASKPASS

configWAYLAND_DISPLAY

// 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

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

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.

// 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 9 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 Score](https://m8ven.ai/badge/mcp/bottobot/defense-mcp-server)](https://m8ven.ai/mcp/bottobot/defense-mcp-server)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: ccdc3f3be66fc9c964850f5eb0e9f33c7efe8580

code hash: 7a48c2d60f09a8e4e075c9d2ac82c77015e7e723a0bcb25649c7ce2b30c24d4f

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