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 skills add coe0718/deskbrid --skill deskbrid-hermes-mcpgit clone --depth 1 https://github.com/coe0718/deskbridWrote 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/skills/coe0718/deskbrid/deskbrid-hermes-mcp)<a href="https://agentmods.dev/skills/coe0718/deskbrid/deskbrid-hermes-mcp"><img src="https://agentmods.dev/badge/skills/coe0718/deskbrid/deskbrid-hermes-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coe0718/deskbrid/deskbrid-hermes-mcp"><img src="https://agentmods.dev/badge/skills/coe0718/deskbrid/deskbrid-hermes-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 35 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00055 | $0.01246 |
| Opus 5.5 | $0.00022 | $0.00498 |
| Sonnet 5.5 | $0.00011 | $0.00249 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
deskbrid-hermes-mcp scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:20129 How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deskbrid Hermes MCP Integration
Wire Deskbrid's 100+ Linux desktop control tools into Hermes as an MCP server. After setup, the agent can control windows, keyboard, mouse, clipboard, screenshots, AT-SPI accessibility, terminals, and more.
Prerequisites: Deskbrid daemon installed and running. See devops/deskbrid-install skill for system installation.
What This Skill Covers
- Start the Deskbrid daemon (if not running)
- Register Deskbrid as a Hermes MCP server
- Test MCP connectivity
- Verify available tool categories
Step 1 — Ensure Daemon Is Running
pgrep -a deskbrid
If no daemon, start it:
nohup deskbrid daemon --dashboard-bind 0.0.0.0 > /tmp/deskbrid.log 2>&1 &
sleep 2
curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:20129
--dashboard-bind 0.0.0.0 makes the web dashboard accessible from LAN. Use 127.0.0.1 on single-user workstations. The dashboard exposes clipboard history, screenshots, and window titles — only bind to 0.0.0.0 on trusted networks.
Step 2 — Register MCP Server
# Check if already registered
hermes mcp list | grep deskbrid
# Register
hermes mcp add deskbrid --command "deskbrid mcp"
This adds to ~/.hermes/config.yaml:
mcp_servers:
deskbrid:
command: deskbrid
args:
- mcp
timeout: 30
Step 3 — Test
hermes mcp test deskbrid
Expected: ✓ deskbrid: connected
Step 4 — Session Restart
MCP servers are loaded at session start. Run /reset or start a new hermes session. After restart, the agent has 100+ new tools.
Available Tool Categories
After MCP registration, the agent gains these tool categories:
| Category | Tools | Examples |
|---|---|---|
| Windows | list, focus, close, minimize, maximize, move, resize, tile | list_windows, focus_window |
| Input | keyboard typing, key combos, mouse, click, scroll, drag | type_text, press_key, mouse_move |
| Clipboard | read, write, history | clipboard_read, clipboard_write |
| Screenshots | capture, OCR, diff | screenshot, screenshot_ocr |
| System | info, battery, idle, power, pressure (PSI) | system_info, system_pressure |
| AT-SPI A11y | tree, get element, click, set value, perform action | get_accessibility_tree, click_element |
| Terminal | create PTY, send input, read output | terminal_create, terminal_send |
| Files | search, read, write, watch | files_search, files_read |
| Audio | volume, mute, sink management | audio_volume, audio_mute |
| Network | WiFi, Bluetooth, connections | network_status, wifi_scan |
| MPRIS | media player control | mpris_play, mpris_pause |
| list printers, print files, manage jobs | print_file, print_list |
|
| Notifications | send, dismiss, history | notify_send, notify_dismiss |
| Keyring | Secret Service credentials | secrets_get, secrets_store |
| Rules | event-triggered automation | rule_create, rule_list |
| Confirmation | approval-gated destructive actions | confirm, deny |
| Agent | inter-agent mailbox messaging | agent_send, agent_check |
| Search | unified cross-surface search | search_query |
| Macros | record and replay action sequences | macro_record, macro_replay |
| Capabilities | supported actions, high-risk listing | capabilities |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 121 lines · 55 tokens per session scan A 96ff4c4cbefb
deskbrid-hermes-mcp is a skill published in the GitHub repository coe0718/deskbrid (31 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,246 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
deskbrid-hermes-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deskbrid-hermes-mcpcoe0718/deskbrid | Skill | 31 | 1mo ago | MIT | A | 55 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |