Search Fragments — Documentation

Two tools: resolve half-remembered queries, or verify a specific claim against current web sources.

Half-remembered, cross-source queries usually take a dozen tabs and five rephrasings. Search Fragments collapses that into one call. Search Fragments is a remote Model Context Protocol (MCP) server with two tools. resolve_fragment: when an agent hits a half-remembered, cross-source query it can’t pin down, it returns a named answer, ranked sources to confirm by eye, or an honest decline — built to decline rather than guess. verify_claim: given a specific factual assertion, checks it against current web sources and returns a calibrated verdict with cited evidence and stated limits. Why agents hallucinate on these queries →

What it’s for

Agents frequently hit queries where a user is describing something they know exists but can't name — a book, film, song, artwork, person, or event. If the input reads like a memory ("there's this thing where…", "somebody who…", "a story about…") rather than a lookup, this is the right tool.

Search Fragments attempts a grounded resolution and returns one of three honest shapes:

  • Resolved — A named answer, with confidence justified by the evidence found.
  • Shortlist — Ranked web sources to read and confirm by eye — results returned, but no confident semantic identification made.
  • No resolution — An explicit no-resolution — not resolvable from the clues given.

Use for

  • a musician who became famous largely for stopping performing
  • somebody who photographed the same view every day until the changes became the artwork
  • a song everybody knew but nobody could identify
  • a novel where the footnotes slowly become the real story

Not for — answer directly or use normal search instead

  • what is the capital of France
  • who directed Jaws
  • name of french artist cubist painting 1948
  • which company bought Instagram in 2012
  • Any well-documented fact or common trivia — this tool adds a multi-second round trip with no accuracy benefit there, and is not reliably correct on well-known items either.

Tool: resolve_fragment

  • Type: read-only (readOnlyHint: true)
  • Input: fragment — a half-remembered query in the user’s own words.
  • Output: a resolution result in one of the three shapes above.
  • Behaviour: built to prefer an honest shortlist or decline over a forced guess.

Tool: verify_claim

Use when you have a specific factual assertion and want to check it against current web sources.

  • Type: read-only (readOnlyHint: true)
  • Input: claim — a concrete, checkable statement.
  • Output: verdict, evidence (web sources), and stated_limits.

Verdict set:

  • supported — multiple independent sources directly confirm the specific claimed detail.
  • partially_supported — sources confirm the entity and domain; the specific detail is pointed toward but not directly stated.
  • insufficient_evidence — sources don’t address the specific claim. Fires freely, including when the entity is well-known but the specific detail is undocumented.
  • unsupported — a credible source explicitly contradicts the claim with an identifiable conflicting statement.

All verdicts are DECIDE-BY-EYE. “supported” means current web sources confirm it — not that the claim is true. The stated_limits field is always present and identifies what the evidence cannot confirm.

Good input: specific, checkable assertions — “Werner Herzog dragged a full-size steamship over a hill during filming of Fitzcarraldo”, “Glenn Gould stopped giving live concerts in 1964”. Not for half-remembered fragments — use resolve_fragment for those.

Connecting

Remote MCP server using streamable HTTP transport.

  • Endpoint: https://searchfragments.com/api/mcp
  • Transport: streamable HTTP
  • Method: POST (GET/SSE not supported)
  • Authentication: optional — anonymous access is the default; free, no signup required
  • Registry ID: com.searchfragments/search-fragments

Example client configuration:

{
  "mcpServers": {
    "search-fragments": {
      "type": "remote",
      "transport": "streamable-http",
      "url": "https://searchfragments.com/api/mcp"
    }
  }
}

A GET request returns a 405 with an explanatory message — the expected healthy response for a browser visit.

Comparison

SF vs. incumbent results across 25 constructed fragments: fragment comparison →

Pricing

The service is currently free to use.

Privacy

See /privacy for what data is handled and how. In short: the verbatim text of each fragment is sent to Anthropic (Claude) and Tavily for processing; tokens are stored only as hashes.

Support & contact

hello@searchfragments.com — for integration questions or data requests.

← Search Fragments