// SCAN REPORT

Hercules MCP

45 tools. 35 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

35 can modify or destroy data

10 read-only

45 tools total

Community server · catalogue entry checked 29/06/2026

How to control Hercules MCP ↓

TOOL MAP

What Hercules MCP exposes to your agents

Read (10) Write / Execute (35) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Hercules MCP tools

Execute · Critical system_start_new_session This tool initiates a new offensive security environment (Kali Linux container) which allows execution of arbitrary penetration testing commands and exploits. Execute · High system_stop_container This tool triggers external operations (container lifecycle management) whose effects depend on implementation—stopping a container halts all running tools, processes, and services within it. Execute · High browser_act This tool executes browser interactions whose effects depend on what element is targeted and what action is performed. Execute · Critical browser_cmd This tool permits arbitrary execution of browser subcommands with no apparent input validation or sandboxing constraints.

35 of Hercules MCP's 45 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Hercules MCP

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

Rate limit write operations

{
  "nuclei_write_template": {
    "limits": [
      {
        "counter": "nuclei_write_template_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "browser_read": {
    "limits": [
      {
        "counter": "browser_read_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Hercules MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON HERCULES →

Instant setup, no code required.

FULL CATALOGUE

All 45 Hercules MCP tools

EXECUTE 33 tools

Execute browser_act Interact with an element (click/fill/type/press/hover/select/check). Execute browser_cmd Escape hatch: run any agent-browser subcommand against the stealth session. Execute browser_eval Run JavaScript in the page and return the result. Execute browser_open Open a URL in a stealth Chromium session. Execute browser_session Manage browser sessions / live-view stream. Execute browser_wait Wait for a selector / ms / text / url / load state. Execute bruteforce_hydra bruteforce_hydra Execute crack_john Offline password cracking using John the Ripper. Hashes written to temp file. Execute ctf_binwalk Firmware/archive analysis and extraction using binwalk. Execute ctf_steghide Steganography analysis and extraction via steghide. Execute fuzz_dirs Directory brute-forcing (gobuster/ffuf). Execute metasploit_generate_payload Generate a payload. Tries RPC first, falls back to msfvenom CLI. Execute metasploit_manage Manage Metasploit sessions and jobs. Execute metasploit_run_module metasploit_run_module Execute metasploit_start_listener Start exploit/multi/handler as a background job to catch reverse shells. Execute ncat Use ncat to connect, listen, or interact with a background listener. Execute network_curl HTTP client (curl) for arbitrary web requests. Execute network_hping3 Packet crafting and firewall testing (hping3). Execute nmap_run_nse_script Run a custom NSE script against a target. Execute nmap_scan Run nmap in quick, aggressive, port, script, or custom mode. Execute nmap_write_nse_script Write custom NSE script and update DB. Execute nuclei_run Run nuclei vulnerability scanner against targets. Execute recon_amass Subdomain enumeration via amass. Execute recon_dns Run DNS lookups with dig or bulk DNS resolution with dnsx. Execute searchsploit Exploit-DB search or exploit retrieval. Execute shell_exec shell_exec Execute shell_exec_background Run a long shell command in the background, returning a job_id. Execute shell_kill_job Kill a running background shell job (useful for stuck commands). Execute sqlmap_run Automated SQL injection suite. Always uses --batch. Execute system_start_new_session system_start_new_session Execute system_stop_container system_stop_container Execute web_scan Run one web fingerprinting scanner selected by tool. Execute web_vuln_scan Run Dalfox XSS scanning or Commix command-injection scanning.

WRITE 2 tools

Write nuclei_write_template Write custom nuclei YAML template to workspace. Write workspace_write_file Write content to a file inside the container workspace (overwrites if exists).

READ 10 tools

Read browser_read Read text/html/value/url/title from the page. Read browser_screenshot Capture a PNG screenshot into the session's workspace directory. Read browser_skill Load agent-browser's own skill/command documentation. Read browser_snapshot Accessibility-tree snapshot with @e refs. Read metasploit_search Search MSF modules by name, CVE, or keyword. Returns matching exploits, auxiliary, and post modules. Read recon_whois Domain OSINT via whois. Read shell_check_job Check the status and read live output of a background shell job. Use tail_lines to control how many lines to r Read system_list_sessions system_list_sessions Read system_network_info system_network_info Read workspace_read_file Read the contents of a file inside the container workspace.

EXPLORE

Related servers

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

FAQ

Questions about Hercules MCP

How do I prevent bulk modifications through Hercules MCP? +

The Hercules MCP server has 2 write tools including nuclei_write_template, workspace_write_file. 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 Hercules MCP.

How many tools does the Hercules MCP server expose? +

45 tools across 3 categories: Execute, Read, Write. 10 are read-only. 35 can modify, create, or delete data.

How do I enforce a policy on Hercules MCP? +

Register the Hercules 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 Hercules MCP tool call.

Deterministic rules across all 45 Hercules MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON HERCULES →

Instant setup, no code required.

45 Hercules MCP tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Hercules'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 →