All servers / Search / Stork: search, scrape and docs
Stork: search, scrape and docs
Web search, page reading and library docs for agents. No key. Routed to the best measured server.
Tested by ConnectATD Hosted serverTested 2026-11-22. Address: https://mcp.stork.ai/core · Registry name: ai.stork/core
Score 95 out of 100. Tested 2026-11-22.
Score breakdown
| Connects and stays up | 20 / 20 | |
|---|---|---|
| Tool descriptions | 18 / 20 | |
| Inputs explained | 12 / 15 | |
| Speed | 15 / 15 | |
| Safety basics | 15 / 15 | |
| Upkeep | 15 / 15 |
What we saw
- Connects and answers the MCP handshake: yes (0.3 seconds)
- Uses an encrypted (https) connection: yes
- Server reports itself as: storkai 2.0.2
- Tools offered: 6 · Parameters with a plain description: 16 of 20
- Official registry entry last updated: 2026-11-20
From the publisher
- No notes.
How hosted servers are graded
Hosted servers run on the publisher's own machines, so we cannot score downloads or install safety. We use six checks instead (connects and stays up 20, tool descriptions 20, inputs explained 15, speed 15, safety basics 15, upkeep 15). Speed is the first call to a safe, read-only tool (when a server marks none, the time to connect and list its tools), using a fresh request where we can so a saved answer cannot hide a slow one. We never call tools that write data or cost money. A server that needs a login or key is not graded. Full method.
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions.
stork_search3 of 3 parameters describedSearch the web. Returns ranked results with titles, addresses and text snippets for a query. The search is run by a web search provider (Exa today), which is named in the reply's `via` field. Results are third-party content.
stork_scrape3 of 3 parameters describedRead one public web page. Returns the page's main content as markdown for a given address. The page is fetched by a page-reading provider (Firecrawl today), which is named in the reply's `via` field. The page is third-party content.
stork_docs3 of 3 parameters describedLook up current documentation for a code library or framework. Returns the passages and code examples that fit a question. The lookup is run by a documentation provider (Context7, or the vendor's own documentation server for Microsoft, AWS and Cloudflare), which is named in the reply's `via` field.
stork_repo3 of 3 parameters describedAnswer a question about the code in a public GitHub repository: how something is implemented, where it lives, how it is used. The answer comes from DeepWiki, which has indexed the repository, and is named in the reply's `via` field. Can take 10 to 20 seconds.
stork_install2 of 2 parameters describedGet the configuration for adding a named MCP server (for example Notion, Supabase, Sentry, Postgres or a browser) to a given client. Returns the config, what the user must supply (a sign-in or keys), and who publishes the server. Where a vendor publishes its own server, that one is returned.
stork_find_server2 of 6 parameters describedFind MCP servers for a task or product (for example: Stripe payments, browser automation). Returns matching servers from Stork's directory, each with how to connect, whether its endpoint answered Stork's last check, how many tokens its tool definitions take, and what Stork's own test calls saw.
Tested by ConnectATD. Spotted a mistake? Tell us.