About Search Fragments
Search Fragments is a hosted MCP server for agents resolving hard-to-place memories about media, places, and studies. It returns an evidence-backed answer, a ranked shortlist, or an explicit no-resolution result instead of guessing.
Key features
- 01Resolves queries from partial clues
- 02Returns evidence-backed answers
- 03Ranks possible matches
- 04Verifies specific claims
- 05Accepts resolution feedback
Use cases
- 01Identify a film from a remembered scene
- 02Find a song from incomplete lyrics
- 03Locate a book or quote from fragments
- 04Check a candidate answer against evidence
MCP support
The remote MCP server exposes `resolve_fragment`, `verify_claim`, and `submit_resolution_feedback` to MCP clients. Basic use requires no authentication; OAuth 2.0 is available for authenticated use.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://searchfragments.com/api/mcpclaude mcp add --transport http com-searchfragments-search-fragments https://searchfragments.com/api/mcp{"mcpServers":{"com-searchfragments-search-fragments":{"type":"http","url":"https://searchfragments.com/api/mcp"}}}Open in Cursor{"servers":{"com-searchfragments-search-fragments":{"type":"http","url":"https://searchfragments.com/api/mcp"}}}Open in VS Code{"mcpServers":{"com-searchfragments-search-fragments":{"type":"http","url":"https://searchfragments.com/api/mcp"}}}{"mcpServers":{"com-searchfragments-search-fragments":{"serverUrl":"https://searchfragments.com/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
3| Parameter | Type | Required | Description |
|---|---|---|---|
| fragment | string | Yes | The half-remembered or fragment-shaped query, in the user's own words. Must be at least 5 characters and describe the thing being recalled by premise, plot, relationship, or context. |
Details
From the project READMESearch Fragments
Resolve half-remembered queries without guessing. A confident answer, a ranked shortlist, or an honest no. For when you half-remember something and can't place it. Half-remembered, cross-source queries usually take a dozen tabs and five rephrasings; Search Fragments collapses that into one call. Not for well-known facts, where normal search is faster.
Tools: resolve_fragment, verify_claim, submit_resolution_feedback
Free. No signup required.
Available in Claude, Cursor, Raycast and GitHub, or add the URL below to any MCP-compatible agent.
{
"mcpServers": {
"search-fragments": {
"url": "https://searchfragments.com/api/mcp"
}
}
}
Why this exists
AI agents tend to become confidently wrong on fragmented queries: partial memories, indirect relationships, missing names. There's real signal in the fragment — enough for a model to recognize the pattern — but not enough to verify an answer from memory alone. The result is fluent, specific, and wrong.
Search Fragments is built to decline rather than guess. Every query resolves to one of three honest shapes:
- Resolved — a named answer, with confidence backed by evidence found.
- Weighted Partial — a ranked shortlist of candidates to decide by eye.
- No Resolution — an explicit "not resolvable from these clues," with no confidence claimed.
In a test against a baseline agent on 50 hard, under-documented fragments, the baseline fabricated three specific wrong answers with no hedge — Search Fragments declined honestly on all three. Full write-up: searchfragments.com/agent-hallucinations.
More on the design philosophy: searchfragments.com/why.
Server details
| Type | Remote, streamable-http MCP server |
| Endpoint | https://searchfragments.com/api/mcp |
| Tools | resolve_fragment (resolve a fragment), verify_claim (check a specific claim), submit_resolution_feedback (report whether a resolution was right) |
| Auth | None required for basic use (free tier). OAuth 2.0 (Authorization Code + PKCE) available for authenticated use. |
| Registry | MCP Registry — com.searchfragments/search-fragments |
See server.json for the full MCP registry manifest.
Links
- Website: searchfragments.com
- Privacy policy: searchfragments.com/privacy
- Terms: searchfragments.com/terms
- Contact: [email protected]
License
MIT. See LICENSE.
About this repository
This repository documents and points to the hosted Search Fragments MCP server. The server itself runs as a managed remote service — there's no local install; connect to the endpoint above from any MCP-compatible client.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.