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 drewburchfield/help-scout-mcp-server --skill helpscout-navigatorgit clone --depth 1 https://github.com/drewburchfield/help-scout-mcp-serverWrote 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/drewburchfield/help-scout-mcp-server/helpscout-navigator)<a href="https://agentmods.dev/skills/drewburchfield/help-scout-mcp-server/helpscout-navigator"><img src="https://agentmods.dev/badge/skills/drewburchfield/help-scout-mcp-server/helpscout-navigator/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/drewburchfield/help-scout-mcp-server/helpscout-navigator"><img src="https://agentmods.dev/badge/skills/drewburchfield/help-scout-mcp-server/helpscout-navigator.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 MCP Rug Pull · line 23 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00065 | $0.04010 |
| Opus 5 | $0.00032 | $0.02005 |
| Sonnet 5 | $0.00013 | $0.00802 |
| Haiku 4.5 | $0.00006 | $0.00401 |
Grade A, and why
helpscout-navigator 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 12d 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HelpScout Navigation
Guide for correctly using the Help Scout MCP gateway. Prevents common mistakes and ensures complete search results.
First Step: Check the Tools Are There
Look for these three tools among your available tools (clients usually prefix them with the server name, e.g. mcp__helpscout__search_help_scout):
search_help_scoutdescribe_help_scoutread_help_scout
If they are available: ✅ Skip to "Critical Rules". You're ready to go.
If they are NOT available, the Help Scout MCP server is not connected in this client. Tell the user, and point them at the setup for their client (see the server README):
- Claude Desktop / claude.ai (including Cowork): install the Desktop Extension (
.mcpbfrom releases), enter the App ID and App Secret in its settings, restart the app. - Claude Code and other CLI clients: register the server (for example
claude mcp add helpscout --env HELPSCOUT_APP_ID=... --env HELPSCOUT_APP_SECRET=... -- npx -y help-scout-mcp-server). Credentials come from the client's process environment, so after setting them, fully restart the client from a fresh shell; a client started before the variables existed never sees them. - Credentials come from Help Scout: profile icon > My Apps > Create Private App, then copy the App ID and App Secret.
Do not proceed with HelpScout operations until the tools are available. If the tools are present but every call fails with an authentication error, the credentials are wrong; re-check them in the client's server config.
Overview
The Help Scout MCP server advertises three tools. Behind them sits a registry of 55 read operations covering conversations, customers, organizations, reports, metadata, and Docs:
| Tool | Purpose |
|---|---|
search_help_scout |
Find operations by intent. Returns up to 8 name + description summaries. |
describe_help_scout |
Get full input schemas for up to 10 named operations. |
read_help_scout |
Execute one operation: {"name": "<operation>", "arguments": {...}} |
What ships with it
3 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.
- 12d ago First seen · 331 lines · 65 tokens per session scan A ab46304c89d1
helpscout-navigator is a skill published in the GitHub repository drewburchfield/help-scout-mcp-server (47 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 4,010 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
rpgmaker-mv-mcp
Use when building, editing or reasoning about an RPG Maker MV game through the RpgMakerMVUltimate MCP server (tools prefixed rpgmaker / the 13 consolidated tools: querydatabase, createdatabaseentry, generatemap, managemapevent, analyzeproject, etc.). Covers the correct workflow so maps, NPCs, chests, shops, doors…
propprofessor-mcp
PropProfessor MCP: sports betting analysis for AI agents. Screens 36+ books, ranks by sharp movement, validates with multi-window consensus. Multi-market (ML/Spread/Total), market aliasing, consensus strength scoring.
policy-support-check
Check supported US consumer subscription refund, cancellation, return, and trial policies with Policy Notaries, a Krafthaus app powered by Decide. Use for support-policy questions and integration tests, not for executing account changes.
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.