mcpbeat Sign in

Sharebench MCP Server

by sharebench Your server? Claim it
answering

Sharebench is answering right now. Last checked 14 min ago. It exposes 2 tools.

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

Uptime history 91 days of history · worst day 0%
91 days agonow
100.0%
Uptime 24h
91 of 91 checks
2
Tools
read from the server
251 ms
Response time
average over 24h
open, no key
Access
streamable-http

Sharebench missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

run in your terminal
claude mcp add registry --transport http https://mcp-public.sharebench.ai
Settings → Connectors → Add custom connector, then paste this address
https://mcp-public.sharebench.ai
~/.codex/config.toml
[mcp_servers.registry]
url = "https://mcp-public.sharebench.ai"
.cursor/mcp.json
{
  "mcpServers": {
    "registry": {
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "registry": {
      "type": "http",
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}

Available tools 2

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

get
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
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.

Endpoints

URLTransportStateLatencyChecked
https://mcp-public.sharebench.ai streamable-http answering 519 ms 14 min ago

Alternatives to Sharebench

same job, measured the same way
AI Skill Directory
by aiskilldir

Search and fetch curated AI agent skills, prompts and MCP servers.

3 tools answering
Paretostudio MCP
by paretostudio

Read, create, and install your ParetoStudio prompts, agents, and skills from any MCP client.

39 installs/wk local only
Qaskills
by pramoddutta

Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.

49 installs/wk local only
Skills Hub
by tinh2

Search & install 13,000+ AI agent skills from skills-hub.ai inside any MCP tool.

97 installs/wk 4 tools answering
Spark - AI Assets Marketplace
by entire-vc

Search and fetch AI agents, skills, prompts and MCP connectors from the Spark marketplace.

6 tools answering
conduitAI
by akbaraziz

Search, browse, and install MCP servers, agents, skills, and plugins from conduitAI.

88 installs/wk local only
MCP Charts
by mcpcharts

Find MCP servers, skills, plugins, agents, prompts and rules for any task.

3 tools answering
A2asearch MCP
by tadas-github

Search 10,000+ AI agents, MCP servers, and CLI tools via A2ASearch from any MCP client.

61 installs/wk local only

Sharebench — questions

Answers built from our own checks of this server.

What can Sharebench do?
It exposes 2 tools, read directly from the server on our last check. Among them: get_by_id, search. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Sharebench working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 251 ms. The bar chart above shows every period we have measured.
How do I connect Sharebench?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Sharebench need an API key?
No. Sharebench completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 2 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Sharebench?
It answers our handshake in 251 ms on average, which is faster than 56% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.