What is site-mcp-consumer?

A guide for connecting one read-only MCP sidecar to a local CampusCopilot snapshot for a single education website. A snapshot is a saved copy of records, and a sidecar is a separate helper service.

It helps connect Canvas, Gradescope, EdStem, or MyUW records, configure the snapshot path, start the matching service, and retrieve site overviews or lists.

It keeps the agent working from local saved data and limits access to one selected site.

site-mcp-consumer — Skill by xiaojiou176-open/campus-copilot

Install

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.

Any agent

npx skills add xiaojiou176-open/campus-copilot --skill site-mcp-consumer

Clone the repo

git clone --depth 1 https://github.com/xiaojiou176-open/campus-copilot

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/xiaojiou176-open/campus-copilot/site-mcp-consumer/github.svg)](https://agentmods.dev/skills/xiaojiou176-open/campus-copilot/site-mcp-consumer)

Your own site

<a href="https://agentmods.dev/skills/xiaojiou176-open/campus-copilot/site-mcp-consumer"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/campus-copilot/site-mcp-consumer/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/xiaojiou176-open/campus-copilot/site-mcp-consumer"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/campus-copilot/site-mcp-consumer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 648 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	$0.00024	$0.00648
Opus 5.5	$0.00010	$0.00259
Sonnet 5.5	$0.00005	$0.00130
Haiku 4.5	$0.00002	$0.00065

Measured 1mo ago against content hash 01ab2b96f2dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

site-mcp-consumer 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 1mo 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.

skills/site-mcp-consumer/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Site MCP Consumer

Use this skill when you want to wire one of the site-scoped read-only MCP sidecars into Codex, Claude Code, Claude Desktop, or another local MCP-capable runtime that should keep CampusCopilot on the snapshot-first side.

Pick the right surface first

If you need cross-site health, provider status, ask_campus-copilot, or export tools, start with the generic server examples under examples/integrations/ instead of a site sidecar.
If you only need one site's records from a snapshot, keep using this skill and @campus-copilot/mcp-readonly.

Inputs

one site name: canvas, gradescope, edstem, or myuw
one snapshot path such as examples/workspace-snapshot.sample.json
one local consumer that can launch a stdio MCP sidecar

Steps

Choose one site MCP binary:
- campus-copilot-mcp-canvas
- campus-copilot-mcp-gradescope
- campus-copilot-mcp-edstem
- campus-copilot-mcp-myuw
Point CAMPUS_COPILOT_SNAPSHOT at a snapshot JSON file.
Run the sidecar with pnpm --filter @campus-copilot/mcp-readonly start:<site>.
Start with get_site_overview, then move to the site-specific list tools.
If your consumer wants a JSON config example, reuse:
- examples/mcp/codex.example.json
- examples/mcp/claude-desktop.example.json
- examples/mcp/codex-repo-root.example.json
- examples/mcp/claude-desktop-repo-root.example.json
If your runtime is OpenClaw-style or another local operator shell, treat those config files as reusable only when it explicitly supports the same mcpServers shape. Otherwise, use the sidecar command directly and follow examples/openclaw-readonly.md.
Keep all claims snapshot-scoped and read-only.

Good fit

inspect one site's current assignments, messages, or events
keep a coding-agent workflow grounded in one snapshot instead of raw browser state
test builder-side integration without reopening live campus sessions

Not a fit

live browser takeover
posting, replying, or submitting on external services
inventing a write-capable plugin contract

Read the full file on GitHub · 59 lines

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.

1mo ago First seen · 59 lines · 24 tokens per session scan A 01ab2b96f2dc

Subscribe to this mod's changes

site-mcp-consumer is a skill published in the GitHub repository xiaojiou176-open/campus-copilot (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 648 once invoked, about $0.0001 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.

Learning and teaching ai browser-extension canvas decision-support gradescope

coursework

Check the user's courses through the cw CLI — Canvas LMS (MIT, Columbia) plus Gradescope. Use for deadlines/homework due, course announcements, Canvas inbox messages from instructors, grades, course lists, downloading course files, or syncing deadlines to macOS Reminders. Not for HTML drawing.

54yyyu/school-mcp · 67 tokens

penecho-canvas

A skill for creating diagrams, interactive previews, and visual explanations on PenEcho Cloud canvases. It can also revise existing canvases using the user's handwriting and annotations.

penecho/penecho · 79 tokens

penecho-canvas-uat

A canvas tool for PenEcho's user-acceptance testing (UAT), where people check that software works as expected. It lets an agent place diagrams, interactive demonstrations, and handwritten feedback beside the chat when the user explicitly selects PenEcho UAT testing.

penecho/penecho · 85 tokens

penecho-mcp

Create, read, or edit PenEcho canvases, including following the user's drawings and notes.

penecho/penecho · 25 tokens

canvas-homework

Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…

98ping/chip · 92 tokens

myopenmath

Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…

98ping/chip · 128 tokens