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 chrischall/alltrails-mcp --skill alltrailsgit clone --depth 1 https://github.com/chrischall/alltrails-mcpWrote 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/chrischall/alltrails-mcp/alltrails)<a href="https://agentmods.dev/skills/chrischall/alltrails-mcp/alltrails"><img src="https://agentmods.dev/badge/skills/chrischall/alltrails-mcp/alltrails/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/chrischall/alltrails-mcp/alltrails"><img src="https://agentmods.dev/badge/skills/chrischall/alltrails-mcp/alltrails.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00085 | $0.02576 |
| Opus 5.5 | $0.00034 | $0.01030 |
| Sonnet 5.5 | $0.00017 | $0.00515 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
alltrails 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 10d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
alltrails-mcp
Unofficial MCP server for AllTrails — read-only access to trail search, details, reviews, photos, weather, and a signed-in user's saved lists / completed trails / activity feed.
⚠️ AllTrails has no public API. This server reverse-engineers the internal one used by alltrails.com, which is fronted by DataDome bot protection and governed by AllTrails' Terms of Service. It may break at any time, and automated use may violate their ToS. Use at your own discretion for your own account.
Setup
Add to .mcp.json in your project or ~/.claude/mcp.json:
{
"mcpServers": {
"alltrails": {
"command": "npx",
"args": ["-y", "alltrails-mcp"]
}
}
}
Every API request routes through the fetchproxy browser bridge — it runs as a same-origin fetch inside your signed-in alltrails.com tab (DataDome fingerprints Node-originated requests, so there is no stored-cookie mode). Requirements: the ContextMint Bridge extension installed (https://github.com/nullnet-app/contextmint-bridge/releases — the fetchproxy extension renamed, same maintainer; public source, .sha256-checkable release zips; use Chrome for now), a signed-in alltrails.com tab open, and a one-time pair-code approval on first use. The x-at-key app key is never stored in code or config — it is captured live from the tab's own API traffic and held in memory only.
Tools
view — slim by default
Every tool marked view? below answers in one of two shapes, and the cheap one
is what you get for free:
view: "compact"(the default) — a slim projection of just the fields you act on. Each tool's row says exactly which.view: "full"— AllTrails' whole untouched record.
You do not pass anything to get the compact answer. Reach for view: "full"
only when you need a field the projection drops — most often route geometry
from alltrails_get_trail.
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.
- 10d ago Changed · +26 lines 8df5de23f08d
- 28d ago Changed 22a570615f2a
- 1mo ago Changed cf5abfe00b3a
- 2mo ago Changed 043403a6de68
- 2mo ago Changed · +19 lines 57f12768a7a8
- 2mo ago First seen · 82 lines · 85 tokens per session scan A d7361d3541e5
alltrails is a skill published in the GitHub repository chrischall/alltrails-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 2,576 once invoked, about $0.0003 per session on Opus 5.5. 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.
alltrails compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alltrailschrischall/alltrails-mcp | Skill | 0 | 3d ago | MIT | A | 85 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |