Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/suzu-testing/metasploit-cursor-harness/msf-mcp-routinggit clone --depth 1 https://github.com/Suzu-Testing/metasploit-cursor-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/msf-mcp-routing)<a href="https://agentmods.dev/rules/suzu-testing/metasploit-cursor-harness/msf-mcp-routing"><img src="https://agentmods.dev/badge/rules/suzu-testing/metasploit-cursor-harness/msf-mcp-routing.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01406 | $0.01406 |
| Opus 5 | $0.00703 | $0.00703 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
msf-mcp-routing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Routing
Always prefer the msf-harness MCP tools over raw msfconsole shell commands.
When to Use MCP
| Operation | MCP Tool | NOT shell |
|---|---|---|
| Search modules | msf_search_modules |
msfconsole -x "search ..." |
| Module details | msf_module_info |
msfconsole -x "info ..." |
| Module options | msf_module_options |
msfconsole -x "show options" |
| List by type | msf_list_modules |
msfconsole -x "show exploits" |
| Running stats | msf_running_stats |
N/A |
| Async job results | msf_module_results |
N/A |
| Query hosts | msf_host_info |
msfconsole -x "hosts" |
| Query services | msf_service_info |
msfconsole -x "services" |
| Query vulns | msf_vulnerability_info |
msfconsole -x "vulns" |
| Query notes | msf_note_info |
msfconsole -x "notes" |
| Query creds | msf_credential_info |
msfconsole -x "creds" |
| Query loot | msf_loot_info |
msfconsole -x "loot" |
| DB status | msf_db_status |
msfconsole -x "db_status" |
| RPC status | msf_status |
msfconsole -x "version" |
| Run exploit | msf_run_exploit |
msfconsole -x "use ...; exploit" |
| Run auxiliary | msf_run_auxiliary_module |
msfconsole -x "use auxiliary/...; run" |
| Run post module | msf_run_post_module |
msfconsole -x "use post/...; run" |
| Check vuln | msf_module_check |
msfconsole -x "use ...; check" |
| Session commands | msf_send_session_command |
msfconsole -x "sessions -i ..." |
| Session info | msf_session_info |
msfconsole -x "sessions -i X" |
| Session script | msf_session_run_script |
sessions -i X then run <script> |
| List sessions | msf_list_active_sessions |
msfconsole -x "sessions" |
| Start handler | msf_start_listener |
msfconsole -x "use multi/handler; ..." |
| List handlers | msf_list_listeners |
msfconsole -x "jobs" |
| Job details | msf_job_info |
msfconsole -x "jobs -v" |
| Stop job | msf_stop_job |
msfconsole -x "jobs -k ..." |
| Kill session | msf_terminate_session |
msfconsole -x "sessions -k ..." |
| Wait for session | msf_wait_for_session |
polling in shell |
| List payloads | msf_list_payloads |
msfconsole -x "show payloads" |
| Generate payload | msf_generate_payload |
msfvenom -p ... |
| Compatible payloads | msf_compatible_payloads |
msfconsole -x "show payloads" after use |
| Lab network info | msf_get_lab_network |
manual YAML reading |
| Upgrade session | msf_session_upgrade |
sessions -u <id> |
| List workspaces | msf_list_workspaces |
msfconsole -x "workspace" |
| Create workspace | msf_create_workspace |
msfconsole -x "workspace -a ..." |
| Switch workspace | msf_set_workspace |
msfconsole -x "workspace ..." |
| Delete workspace | msf_delete_workspace |
msfconsole -x "workspace -d ..." |
| Import scan data | msf_db_import |
msfconsole -x "db_import ..." |
| Run nmap + import | msf_db_nmap |
msfconsole -x "db_nmap ..." |
| Clean up jobs | msf_cleanup_jobs |
msfconsole -x "jobs -K" |
| Console command | msf_console_execute |
msfconsole -x "..." |
| List consoles | msf_console_list |
N/A |
| Session sysinfo | msf_session_sysinfo |
sessions -i X then sysinfo |
| Session getuid | msf_session_getuid |
sessions -i X then getuid |
| Session processes | msf_session_ps |
sessions -i X then ps |
| Download file | msf_session_download |
sessions -i X then download |
| Upload file | msf_session_upload |
sessions -i X then upload |
| List routes | msf_route_list |
msfconsole -x "route print" |
| Add route | msf_route_add |
msfconsole -x "route add ..." |
| Remove route | msf_route_delete |
msfconsole -x "route remove ..." |
| Autoroute | msf_autoroute |
run post/multi/manage/autoroute |
| Report host | msf_report_host |
msfconsole -x "hosts -a ..." |
| Store credential | msf_credential_add |
msfconsole -x "creds -a ..." |
| Add note | msf_db_add_note |
msfconsole -x "notes -a ..." |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 83 lines · 1,406 tokens per session scan A 0ddfb61f3e42
msf-mcp-routing is a cursor rule published in the GitHub repository Suzu-Testing/metasploit-cursor-harness (3 stars, last pushed 12d ago), licensed MIT. It adds 1,406 tokens to every session, about $0.0070 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.