# Upshift

> Audit a site's structured data and llms.txt, match a trade to a template, and quote real prices.

- name: com.upshiftsites/mcp
- version: 1.0.3
- connection class: R0 (autonomous)
- trust: 92/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.upshiftsites%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.upshiftsites%2Fmcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "upshiftsites": {
      "type": "http",
      "url": "https://mcp.upshiftsites.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% ~updated-63d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: upshift_template_match (destructiveHint, idempotentHint); upshift_site_audit (destructiveHint, idempotentHint); upshift_quote (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 699 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 4 resolved packages
- pass `deps.mcp_sdk_version`: @modelcontextprotocol/server 2.1.0, no known advisory
- pass `deps.resolvable`: upshift-mcp@1.0.3 resolved: 4 packages

- tools: 3, about 699 tokens to load them all
- tool set hash: 4d8564b227aef4c3f79c1dad53aa9590
- badge: [![protogrid quality](https://protogrid.dev/badge/com.upshiftsites/mcp.svg)](https://protogrid.dev/servers/com.upshiftsites/mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm upshift-mcp@1.0.3: resolved, 3 dependencies, MCP SDK @modelcontextprotocol/server 2.1.0

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.upshiftsites.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9655172)

## Packages

- npm upshift-mcp@1.0.3

## Tools (3)

- `upshift_quote`: Return Upshift's real prices. job_type 'mcp' covers MCP server work (registry listing, live tool preview, spec upgrade, full build); 'website' covers website templates and done-for-you launches. These are the actual listed prices, not estimates. Use when someone asks what a job costs, what a tier includes, or how long it takes. The figures are generated from the live store catalog, so this cannot quote a price that is not sold; it makes no network call and the same arguments always return the same answer.
- `upshift_site_audit`: Fetch a live website and report how legible it is to search engines and AI assistants: structured data (JSON-LD), llms.txt, robots.txt, title and meta description, headings, image alt text, HTTPS and document weight. Returns findings with severity and a 0-100 score. Use this to check a real site before recommending changes to it. Makes one outbound request to the URL given, so it only sees what a fetch can establish — never rendering or browser metrics. Refuses private, loopback and link-local addresses, and reports a page as unreachable rather than scoring the error body.
- `upshift_template_match`: Given an industry or trade (and optionally what the business needs), rank Upshift's 14 website template lines and return the best three, each with a live demo link, the store link, real prices, and the words that made it match. Use when someone asks what a website for a given trade should look like or cost. Answers from a catalog held in the server, so it makes no network call and returns no matches — rather than a forced one — when the trade is outside the 14 lines.