New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
// SCAN REPORT

Kali Security MCP

194 tools. 142 can modify or destroy data without limits.

142 write tools that can modify data. Rate limits recommended.

Last updated:

142 can modify or destroy data
52 read-only
194 tools total

Community server · catalogue entry checked 14/08/2026

How to control Kali Security MCP ↓

TOOL MAP

What Kali Security MCP exposes to your agents

Read (52) Write / Execute (142) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
High Risk

The most dangerous Kali Security MCP tools

Execute · Critical adaptive_execute_strategy The tool executes adaptive penetration testing strategies through automated workflows on a Kali-integrated security platform. Execute · Critical agent_run Tool likely executes arbitrary security operations given server context and empty description; high misuse risk. Execute · Critical authorized_comprehensive_security_assessment This tool triggers automated execution of security testing workflows across multiple Kali Linux utilities. Execute · High authorized_controlled_validation This tool executes validation/testing operations as part of a penetration testing framework (Kali Security MCP context).

142 of Kali Security MCP's 194 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Kali Security MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Kali Security MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "add_ctf_challenge": {
    "limits": [
      {
        "counter": "add_ctf_challenge_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "adaptive_get_execution_status": {
    "limits": [
      {
        "counter": "adaptive_get_execution_status_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Kali Security MCP — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON KALI SECURITY →

Instant setup, no code required.

FULL CATALOGUE

All 194 Kali Security MCP tools

EXECUTE 129 tools
Execute adaptive_cmdi_test 自适应命令注入测试 Execute adaptive_create_execution_context 创建自适应执行上下文 Execute adaptive_execute_strategy 执行自适应策略 Execute adaptive_intelligent_orchestration 智能编排多目标自适应攻击 Execute adaptive_network_penetration 自适应网络渗透测试 - 智能化网络攻击。 Execute adaptive_sqli_test 自适应SQL注入测试 - 智能检测和利用 Execute adaptive_web_penetration 自适应Web渗透测试 - 智能化Web应用攻击。 Execute adaptive_xss_test 自适应XSS测试 - 上下文感知的XSS检测 Execute add_chain_step add_chain_step Execute agent_run agent_run Execute aircrack_attack aircrack_attack Execute apt_comprehensive_attack 执行APT综合攻击链 - 全面的多向量并发攻击。 Execute apt_network_penetration 执行APT网络渗透攻击链 - 自动化多阶段网络渗透测试。 Execute apt_web_application_attack 执行APT Web应用攻击链 - 自动化多阶段Web应用渗透。 Execute arp_scan Execute arp-scan for network discovery. Execute auth_bypass_test 认证绕过测试 - 内置工作流 Execute authorized_comprehensive_security_assessment Run authorized full-chain assessment using neutral external naming. Execute authorized_controlled_validation Run controlled validation phase only when allowed_actions permits it. Execute authorized_credential_assessment Run authorized credential audit phase only when allowed_actions permits it. Execute authorized_environment_review Run environment review phase only when allowed_actions permits it. Execute authorized_injection_verification Run non-destructive injection verification only (no dump/exfiltration). Execute authorized_network_exposure_assessment Run authorized network exposure assessment with phase-level output. Execute authorized_template_validation Run template-based security validation with constrained severity scope. Execute authorized_web_application_assessment Run authorized web assessment with exposure review and vuln validation. Execute auto_reverse_analyze 自动选择可用工具进行逆向分析 - 智能工具选择 Execute bandit_scan bandit_scan Execute bettercap_attack bettercap_attack Execute browser_click 模拟人工点击页面元素（带随机延迟和鼠标移动模拟） Execute browser_close_session 关闭浏览器会话并保存状态（cookies/storage持久化到磁盘） Execute browser_execute_js 在浏览器上下文中执行JavaScript代码 Execute browser_intercept_request browser_intercept_request Execute browser_navigate 在已有会话中导航到新页面 Execute browser_start_session browser_start_session Execute browser_type_text browser_type_text Execute brutespray_attack brutespray_attack Execute bully_attack Execute bully for WPS attacks. Execute code_audit_comprehensive code_audit_comprehensive Execute compile_task_handoff Compile handoff/progress for resume (do-not-rescan + next_actions). Execute comprehensive_recon comprehensive_recon Execute continue_from_handoff Resume plan from last handoff without forcing full rescan. Execute create_attack_chain 创建攻击链。 Execute cross_validate_vulns 交叉验证黑盒和白盒发现的漏洞，提升置信度。 Execute crowbar_attack crowbar_attack Execute ctf_pwn_solver ctf_pwn_solver Execute ctf_quick_scan CTF快速扫描 - 针对CTF环境优化的快速漏洞发现。 Execute ctf_web_attack CTF Web攻击链 - 专门针对CTF Web题目的攻击。 Execute detect_blind_vulnerability 盲注漏洞检测 - 基于响应差异 Execute dirb_scan 使用 Dirb 执行目录枚举。 Execute dnsenum_scan 使用 Dnsenum 执行 DNS 枚举。 Execute dnsrecon_scan dnsrecon_scan Execute enum4linux_scan Execute Enum4linux Windows/Samba enumeration tool. Execute execute_command Execute an arbitrary command on the Kali server. Execute fast_reconnaissance 执行快速侦察工作流。 Execute feroxbuster_scan 使用 Feroxbuster 执行目录与资源爆破。 Execute ffuf_scan ffuf_scan Execute fierce_scan 使用 Fierce 执行 DNS 侦察。 Execute flawfinder_scan flawfinder_scan Execute fping_scan Execute fping for fast ping sweeps. Execute fuzz_all_params 全参数模糊测试 - 自动识别并测试所有参数 Execute fuzz_parameter fuzz_parameter Execute generate_attack_paths 生成针对目标的APT攻击路径。 Execute generate_poc_from_current_session 从当前活跃会话生成PoC - 无需指定会话ID，直接从当前会话生成。 Execute generate_poc_from_session 从指定攻击会话生成PoC - 自动分析攻击链并生成多种格式的PoC。 Execute ghidra_analyze_binary 使用Ghidra分析二进制文件 - NSA开源逆向分析工具 Execute gobuster_scan gobuster_scan Execute grpc_call grpc_call Execute hashcat_crack hashcat_crack Execute http_compare 比较两个HTTP响应的差异 - 用于盲注检测 Execute http_replay 重放历史HTTP请求，可修改参数 Execute http_send http_send Execute http_send_raw 发送原始HTTP请求 - 完全控制请求格式 Execute http_session_manage http_session_manage Execute httpx_probe httpx_probe Execute hydra_attack hydra_attack Execute intelligent_apt_campaign 智能APT攻击活动 - 最高级别的自适应攻击。 Execute issue_vulnerability issue_vulnerability Execute john_crack john_crack Execute joomscan_scan Execute joomscan for Joomla security testing. Execute kali_run kali_run Execute llm_auto_pentest llm_auto_pentest Execute masscan_fast_scan masscan_fast_scan Execute medusa_attack 使用 Medusa 执行口令验证测试。 Execute metasploit_run Execute a Metasploit module. Execute multi_target_execute_batch 批量执行多目标攻击任务 Execute multi_target_orchestrate 执行多目标攻击编排 Execute ncrack_attack 使用 Ncrack 执行网络服务凭据验证。 Execute netdiscover_scan netdiscover_scan Execute nikto_scan Execute Nikto web server scanner. Execute nmap_scan nmap_scan Execute nuclei_cve_scan Execute Nuclei CVE vulnerability scan. Execute nuclei_network_scan Execute Nuclei network security scan. Execute nuclei_scan nuclei_scan Execute nuclei_technology_detection Execute Nuclei technology detection scan. Execute nuclei_web_scan Execute Nuclei web application security scan. Execute parallel_directory_scanning 并行执行多个目标的目录扫描。 Execute parallel_port_scanning 并行执行多个目标的端口扫描。 Execute patator_attack patator_attack Execute pixiewps_attack pixiewps_attack Execute proxy_start 启动代理服务器 - 用于流量拦截 Execute pwn_comprehensive_attack pwn_comprehensive_attack Execute quick_pwn_check quick_pwn_check Execute radare2_analyze_binary 使用Radare2分析二进制文件 - 开源逆向分析工具 Execute reaver_attack Execute Reaver for WPS PIN attacks. Execute recon_ng_run Execute recon-ng for reconnaissance. Execute run_playbook Run a named playbook (web_surface | api_surface | auth_surface | svc_surface). Execute run_surface_chain run_surface_chain Execute run_surface_chain_multi run_surface_chain_multi Execute scan_start Start a heavy scan in background; returns job_id immediately. Execute scan_wait Block until an async scan job finishes or timeout_s elapses. Execute semgrep_scan semgrep_scan Execute sqlmap_scan Execute SQLmap SQL injection scanner. Execute start_adaptive_apt_attack start_adaptive_apt_attack Execute start_attack_session 开始新的攻击会话 - 启动自动日志记录和PoC生成。 Execute start_task Create/open a task workspace and seed target graph nodes. Execute subfinder_scan Execute Subfinder for fast subdomain discovery. Execute submit_apt_attack_chain 提交APT攻击链工作流 - 基于知识图谱的智能化并发攻击。 Execute submit_concurrent_task 提交并发任务。 Execute submit_workflow submit_workflow Execute trigger_next_attack_phase 手动触发下一攻击阶段 - 强制进入下一轮攻击。 Execute verify_finding Verify a candidate finding by replaying command and matching expected_signal. Execute verify_vulnerability 验证候选漏洞 (candidate → verified/failed)。 Execute wfuzz_scan 使用 Wfuzz 执行参数与路径模糊测试。 Execute whatweb_scan whatweb_scan Execute workflow_execute 执行测试工作流 Execute wpscan_scan wpscan_scan Execute ws_connect 建立WebSocket连接 Execute ws_fuzz WebSocket模糊测试 Execute ws_send ws_send Execute yersinia_attack yersinia_attack
WRITE 13 tools
Write add_ctf_challenge 添加CTF题目到当前会话。 Write create_ctf_session 创建CTF竞赛会话。 Write disable_ctf_mode 禁用CTF竞赛模式，返回正常渗透测试模式。 Write enable_ctf_mode 启用CTF竞赛模式。 Write end_attack_session 结束当前攻击会话 - 完成日志记录并保存会话数据。 Write export_task_summary Export task report: JSON + Markdown primary; optional docx (python-docx). Write graph_mark_dead Mark a graph node dead so it stops generating next actions. Write graph_upsert Upsert a graph node. next_checks is comma-separated. meta_json is optional JSON object. Write log_attack_step log_attack_step Write multi_target_add_target 添加新目标到多目标协调系统 Write proxy_add_rule proxy_add_rule Write task_timeline Read-only action_log timeline (what/when). No new write path. Write workflow_define 定义测试工作流
READ 52 tools
Read adaptive_get_execution_status 获取执行上下文状态 Read adaptive_get_insights 获取自适应执行洞察 Read agent_status 多智能体集群健康与统计信息。 Read amass_scan 使用 Amass 执行子域名与资产枚举。 Read analyze_attack_chain 评估攻击链可��性 (0-100分)。 Read analyze_response 深度响应分析 - 漏洞指标检测 Read attack_coverage ATT&CK technique label coverage for task findings (report appendix; not a runtime driver). Read authorized_asset_inventory Build authorized external asset inventory (subdomains + live hosts). Read authorized_surface_mapping Perform authorized attack-surface mapping (non-destructive). Read authorized_web_exposure_review Review web exposure through content discovery and service checks. Read binwalk_analysis binwalk_analysis Read browser_extract_content browser_extract_content Read browser_get_network_log browser_get_network_log Read browser_heartbeat_status browser_heartbeat_status Read browser_list_sessions 列出所有活跃的浏览器会话 Read browser_screenshot 截取页面截图（支持全页面和元素截图） Read extract_endpoints 从响应中提取端点和API路径 Read fingerprint_target 目标技术指纹识别 Read get_adaptive_attack_status 获取自适应攻击状态 - 查看攻击进展和发现的信息。 Read get_attack_chains 查询攻击链列表。 Read get_attack_session_details 获取攻击会话详情 - 查看指定会话的完整攻击历史。 Read get_attack_strategy 获取攻击策略推荐 - 基于历史成功率 Read get_concurrent_system_stats 获取并发任务系统统计信息。 Read get_ctf_challenges_status 获取所有CTF题目的状态。 Read get_detected_flags 获取所有检测到的Flag。 Read get_recommended_payloads 获取推荐的Payload - 基于历史数据和目标特征 Read get_task Get task meta, graph summary, findings counts and recent actions. Read get_task_status 获取任务状态。 Read get_vuln_candidates 获取待验证的候选漏洞列表 (按严重程度排序)。 Read get_vuln_report 导出漏洞评估报告。 Read get_workflow_status 获取工作流状态。 Read graph_next_actions List next actions from graph (optionally include insight-sourced checks). Read graph_query Query graph nodes. Read grpc_reflect gRPC服务反射 - 获取服务定义 Read http_history 查看HTTP请求历史 Read identify_attack_surfaces 基于目标信息识别攻击面。 Read list_attack_sessions 获取所有攻击会话列表 - 查看历史和当前的所有攻击会话。 Read list_poc_templates 获取可用的PoC模板 - 查看系统支持的所有PoC生成模板。 Read multi_target_get_status 获取多目标协调系统状态 Read observe_task Observer side-channel: detect duplicate tool calls / empty streaks; advise only by default. Read propose_insights Insight branch: produce graph-bound Hypothesis candidates only (never drives executor). Read proxy_get_intercepted 获取已拦截的请求列表 Read reverse_tool_check 检查可用的逆向分析工具 - 检测本机逆向工程工具 Read scan_collect Poll an async scan job; returns running/done/expired/not_found + result. Read scan_jobs List currently running async scan jobs. Read searchsploit_search Search exploit database using searchsploit. Read server_health Check the health status of the Kali API server. Read shellcheck_scan shellcheck_scan Read sherlock_search sherlock_search Read sublist3r_scan 使用 Sublist3r 执行子域名枚举。 Read task_status Real-time task dashboard: phase, graph size, verified count, recent actions, report paths. Read theharvester_osint theharvester_osint
EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

UnClick 1662 tools
automation
Delx Mcp A2a 1082 tools
automation
Delx Protocol — Agent Recovery & Continuity 1076 tools
automation
Nodebench 824 tools
automation
MCP Framework Personal 811 tools
automation
Delx MCP Server 740 tools
automation
Binance MCP Server 734 tools
automation
Crawlora 728 tools
automation
FAQ

Questions about Kali Security MCP

How do I prevent bulk modifications through Kali Security MCP? +

The Kali Security MCP server has 13 write tools including add_ctf_challenge, create_ctf_session, disable_ctf_mode. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Kali Security MCP.

How many tools does the Kali Security MCP server expose? +

194 tools across 3 categories: Execute, Read, Write. 52 are read-only. 142 can modify, create, or delete data.

How do I enforce a policy on Kali Security MCP? +

Register the Kali Security MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Kali Security MCP tool call.

Deterministic rules across all 194 Kali Security MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON KALI SECURITY →

Instant setup, no code required.

194 Kali Security MCP tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Kali Security's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.