Sharebench

ai.sharebench/registrysharebench.aistreamable-httpv0.1.1Scanned 24 hours ago

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

2 tools: 2 only read.

Reads private data · 1
Reads text others write · 0
Can send data out · 0
No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

Run the operations that matter as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

2 tools

Only reads 2Looks things up and changes nothing.Show 2 read-only tools

get_by_idFetch the full SKILL.md content and metadata for a single artifact.No findings
Why it is in this group
- The name "get_by_id" says "get": a word for reading.
Description, as the server wrote it
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>`.
searchSearch this workspace's published artifacts (skills, agents, workflows, and knowledge documents in SKILL.md format).Reads private dataNo findings
Why it is in this group
- The name "search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "document": it reads documents.
Description, as the server wrote it
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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.

Reads private data1: Reads files, mail, messages, databases, secrets, calendars or repositories.; search
Reads text others write0: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Oct 22, 2026, 14:21 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 0
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: not observed
RFC 9728 protected resource metadata: not observed
Authorization servers: not observed
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http registry https://mcp-public.sharebench.ai

claude mcp add --transport http registry https://mcp-public.sharebench.ai

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__registry__search",
      "mcp__registry__get_by_id"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as registry. Review it before you use it.

Capability tags behind 1 rule

mcp__registry__search private-data

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/ai.sharebench/registry/verify?hash=356f813e6d9fbc9e225fdf39c4da7aa0c6e699eacbfe33d9f12ccc838431cd3d" | jq -e '.changed == false'

Pinned hash 356f813e6d9f, from Oct 21, 2026, 18:41 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/ai.sharebench/registry/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/ai.sharebench/registry.svg)](https://anlyon.dev/servers/ai.sharebench/registry)

Source: MCP Registry. Synced Oct 21, 2026, 17:43 UTC.