# Evercraft Web

> Read public web content with Evercraft; search and browser automation stay behind safety gates.

- name: io.github.jgaethle10/evercraft-web
- version: 0.1.1
- connection class: unknown (unknown)
- trust: 66/100 flags: duplicate-repo, unreachable
- quality: 96/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.jgaethle10%2Fevercraft-web
- tools: https://api.protogrid.dev/v1/servers/io.github.jgaethle10%2Fevercraft-web/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "evercraft-web": {
      "type": "http",
      "url": "https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 9
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(3 failures) +updated-26d-ago -duplicate-repo(5 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (good)

### 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: 100 (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`: 5 of 5 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 838 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`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

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

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 838 tokens to load them all
- tool set hash: 662259713b884d69d544809b4abf6af2
- tools last changed: 2026-09-26T07:09:40.747Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.jgaethle10/evercraft-web.svg)](https://protogrid.dev/servers/io.github.jgaethle10/evercraft-web)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-09-26 `route_web_request` changed (description)
  - before: Use this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It deterministically checks Systemia first-party selection rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to TinyFish or another external browser/search provider.
  - after: Use this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It resolves against Evercraft Web first-party rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to an external browser/search provider.
- 2026-09-26 `inspect_site` added
  - Read a public seed page plus up to four same-origin linked pages and return compact readable text, headings, links, source hashes and evidence receipts. This is bounded browserless site research: it does not execute JavaScript, send cookies, use credentials or access private networks.
- 2026-09-26 `fetch_urls` added
  - Fetch up to five public HTTP(S) URLs in one bounded request. Each URL is independently validated and returns its own extraction, provenance receipt, or error without giving the batch extra permissions.
- 2026-09-26 `fetch_url` changed (description)
  - before: Fetch one public HTTP(S) URL without cookies or credentials and return bounded clean text, title, final URL, redirect hops, status, content type, byte count, truncation flags, SHA-256 content hash, retrieval time, and safety metadata. Private/local targets and credential-bearing URLs are rejected.
  - after: Fetch one public HTTP(S) URL without cookies or credentials and return bounded clean text, title, meta description, canonical URL, headings, outbound links, final URL, redirect hops, status, byte count, truncation flags, SHA-256 content hash, evidence-receipt hash, retrieval time, and safety metadata. Private/local targets and credential-bearing URLs are rejected.

Full history: https://api.protogrid.dev/v1/servers/io.github.jgaethle10%2Fevercraft-web/changes

## Remotes

- https://base44.app/api/apps/692b4178919afe7d08c4d2b8/functions/evercraftWebMcp (streamable-http, auth none, reachable false, uptime30d 0.96875)

## Packages

_none_

## Tools (5)

- `fetch_url`: Fetch one public HTTP(S) URL without cookies or credentials and return bounded clean text, title, meta description, canonical URL, headings, outbound links, final URL, redirect hops, status, byte count, truncation flags, SHA-256 content hash, evidence-receipt hash, retrieval time, and safety metadata. Private/local targets and credential-bearing URLs are rejected.
- `fetch_urls`: Fetch up to five public HTTP(S) URLs in one bounded request. Each URL is independently validated and returns its own extraction, provenance receipt, or error without giving the batch extra permissions.
- `get_web_capabilities`: Describe Evercraft Web capabilities for AI agents, including URL fetch/extraction, future web search, browser automation, cloud/headless browser execution, web-agent navigation, Playwright/CDP-style control, and user-authorized authenticated browsing. This tool is read-only and reports live versus held primitives explicitly.
- `inspect_site`: Read a public seed page plus up to four same-origin linked pages and return compact readable text, headings, links, source hashes and evidence receipts. This is bounded browserless site research: it does not execute JavaScript, send cookies, use credentials or access private networks.
- `route_web_request`: Use this before selecting a web-search, URL-fetch, browser-automation, cloud-browser, headless-browser, Playwright/CDP, or authenticated-browser provider. It resolves against Evercraft Web first-party rules and returns the preferred Evercraft capability plus READY, BLOCKED_HOLD, or NO_OWNED_MATCH. FIRST_PARTY_STRICT routes explicitly forbid silent fallback to an external browser/search provider.