# Sharebench

> Sharebench — search & pull AI skills, agents, prompts & playbooks (SKILL.md) into any MCP client

- name: ai.sharebench/registry
- version: 0.1.1
- connection class: R0 (autonomous)
- trust: 75/100 flags: no-repository
- quality: 76/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.sharebench%2Fregistry
- tools: https://api.protogrid.dev/v1/servers/ai.sharebench%2Fregistry/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "sharebench": {
      "type": "http",
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-95% ~updated-118d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 76/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 2 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_by_id (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 903 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: n/a (weight 15)

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

- tools: 2, about 903 tokens to load them all
- tool set hash: 13a8ded591dd462872e02498e135cdbf
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.sharebench/registry.svg)](https://protogrid.dev/servers/ai.sharebench/registry)
- 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._

## Remotes

- https://mcp-public.sharebench.ai (streamable-http, auth none, reachable true, uptime30d 0.94690263)

## Packages

_none_

## Tools (2)

- `get_by_id`: Fetch the full SKILL.md content and metadata for a single artifact. Provide EXACTLY ONE of `artifactId` (the UUID returned by `search`) or `slug` (the URL-safe identifier, e.g. from a `/p/<slug>` link). Passing both or neither returns a `validation_failed` error. Use this after `search` to retrieve the body of a hit the user wants to read, summarize, apply, or fork. Returns the artifact's name, description, type, contributor, version, timestamps, the full SKILL.md text (YAML frontmatter + markdown body, up to 256 KB), the number of bundled extras (`bundledCount`), their filenames (`bundledFilenames`), per-file metadata in `bundledFiles` (each entry has `key`, `filename`, and `originalRef` — the EXACT body-relative reference string the importer matched, or `null` when the file was bundled without a body reference; use this to translate a link span in the body back to its bundle filename), and the public-surface fields `slug`, `authorCredit`, `industries`. To fetch a bundled extra, read it as a resource at `artifact://<artifactId>/bundled/<filename>`.
- `search`: Search this workspace's published artifacts (skills, agents, workflows, and knowledge documents in SKILL.md format). Returns ranked metadata — name, description, type, contributor, timestamps, bundledCount, slug, authorCredit, and industries — but NOT the full body. To read an artifact's content, call `get_by_id` with the returned `artifactId` (or `slug`), or read it as a resource at `artifact://<artifactId>`. Use this whenever the user wants to find, discover, browse, or filter existing artifacts before reading or contributing. Modes: `hybrid` (default; combines lexical and semantic ranking via reciprocal rank fusion — best for most queries), `bm25` (exact-keyword or name lookups), `semantic` (concept matching when the user's terms differ from artifact text). Pass `industries: ['marketing', 'legal']` to narrow results to artifacts tagged with ANY of those industries (keyword-array overlap). If hybrid silently degrades because the embedding service is unavailable, the response's `warnings` array will contain `embedding_degraded:hybrid-fell-back-to-bm25` — surface this to the user if precision matters.