Connect Search Fragments and your agent gets 2 tools, among them resolve_fragment, verify_claim. It answers at https://searchfragments.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.
Resolves half-remembered books, films, songs and people into a cited answer, a shortlist or a no.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
resolve_fragment | Call resolve_fragment when a user describes something they can only half-remember — a book, film, song, artwork, person, or event they know exists but can't name — instead of asking a direct question. If the input reads like a memory ("ther Inputs: fragment |
verify_claim | Call verify_claim when you have a specific factual assertion and want to know whether current web sources support it. Takes a claim as a natural-language statement; returns a verdict with cited evidence and stated limits. Verdict set: - "su Inputs: claim |
Every block below points at https://searchfragments.com/api/mcp. Pick your client and copy.
claude mcp add --transport http search-fragments https://searchfragments.com/api/mcp
{
"mcpServers": {
"search-fragments": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://searchfragments.com/api/mcp"]
}
}
}{
"mcpServers": {
"search-fragments": {
"url": "https://searchfragments.com/api/mcp"
}
}
}{
"servers": {
"search-fragments": {
"type": "http",
"url": "https://searchfragments.com/api/mcp"
}
}
}{
"context_servers": {
"search-fragments": {
"url": "https://searchfragments.com/api/mcp"
}
}
}{
"mcpServers": {
"search-fragments": {
"serverUrl": "https://searchfragments.com/api/mcp"
}
}
}{
"mcpServers": {
"search-fragments": {
"url": "https://searchfragments.com/api/mcp"
}
}
}name: Search Fragments
version: 0.0.1
schema: v1
mcpServers:
- name: Search Fragments
type: streamable-http
url: https://searchfragments.com/api/mcp{
"mcpServers": {
"search-fragments": {
"httpUrl": "https://searchfragments.com/api/mcp"
}
}
}{
"mcpServers": {
"search-fragments": {
"type": "http",
"url": "https://searchfragments.com/api/mcp"
}
}
}{
"mcpServers": {
"search-fragments": {
"url": "https://searchfragments.com/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fsearchfragments.com%2Fapi%2Fmcp&type=streamable_http&id=search-fragments&name=Search%20Fragments
It answered our last check on 19 October 2026 in 506 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by searchfragments.com and served from searchfragments.com, the vendor's own domain: https://searchfragments.com/api/mcp.
2, as returned by the server's own tools/list on 11 September 2026: resolve_fragment, verify_claim.
It answered our last check on 19 October 2026 in 506 ms. Over 6 checks since 10 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://searchfragments.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.searchfragments. Endpoint host: searchfragments.com. ARD identifier: urn:air:com.searchfragments:mcp:search-fragments.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.