What is mcp-roots-snapshot-paging?

A design pattern for adding safe file and folder reading to an MCP server. MCP (Model Context Protocol) lets an AI agent use tools and read structured resources.

Use it to add access requests, file snapshots, folder snapshots, path validation, authorization, and paginated resource responses to an MCP server.

It prevents unsafe paths, directory traversal, and symlink escapes while keeping existing tools working. It also gives the agent a consistent way to read large results in pages.

How alonf/MCPPythonDemo configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to alonf/MCPPythonDemo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/alonf/MCPPythonDemo/master/.squad/skills/mcp-roots-snapshot-paging/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/alonf/MCPPythonDemo

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging/github.svg)](https://agentmods.dev/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging)

Your own site

<a href="https://agentmods.dev/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging"><img src="https://agentmods.dev/badge/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging"><img src="https://agentmods.dev/badge/skills/alonf/mcppythondemo/mcp-roots-snapshot-paging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 316 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00316
Opus 5.5	$0.00000	$0.00126
Sonnet 5.5	$0.00000	$0.00063
Haiku 4.5	$0.00000	$0.00032

Measured 2mo ago against content hash 5453d31b3b10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-roots-snapshot-paging 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 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.

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.

.squad/skills/mcp-roots-snapshot-paging/SKILL.md · 39 lines

What it actually says

MCP Roots + Snapshot Paging Skill

Use When

You need to add a safe sandboxed read surface to an MCP server without breaking older tools.

Pattern

Keep the new sandbox feature additive:
- preserve older tools unchanged
- add a dedicated request_*_access tool plus a dedicated snapshot tool
Put all normalization and authorization in one validator:
- absolute-path requirement
- traversal rejection
- supported-root restriction
- symlink-escape rejection
- allowed-root match before reading
Reuse the existing snapshot/resource UX:
- tool returns {resource_uri, paginated_resource_template}
- resource returns metadata + entries + pagination
Page different source kinds with the same envelope:
- file snapshots → line entries
- directory snapshots → deterministic child metadata entries
Tell the model the order explicitly:
- request_*_access first for blocked paths
- create_*_snapshot second
- read_resource third
Be defensive with MCP resource query handling:
- register the paged template
- also parse ?limit=...&offset=... if it leaks through the base {id} route

Reference Files

src/mcp_linux_diag_server/tools/proc_snapshots.py
src/mcp_linux_diag_server/server.py
src/mcp_linux_diag_server/client.py
tests/test_proc_snapshots.py
tests/test_m7_http.py

Changes

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 · 39 lines · 0 tokens per session scan A 5453d31b3b10

Subscribe to this mod's changes

mcp-roots-snapshot-paging is a skill published in the GitHub repository alonf/MCPPythonDemo (0 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 316 tokens. 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.

Building agents

mcp-roots-snapshot-paging next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-roots-snapshot-pagingalonf/MCPPythonDemo	Skill	0	6mo ago	MIT	A	0	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

MCPPythonDemo: Skill for Claude Code