MCP App Store
by KeenEthics
Search Fragments icon

Search Fragments MCP Server for Claude

By Search Fragments

Overview

Search Fragments is a gate. Before your agent spends effort on something only half-remembered — a book, film, song, artwork, person, place or event — SF tells it whether that thing can be reached. Describe what you remember, for example "the Dickens novel he never finished, about an opium-smoking choirmaster", and Search Fragments looks for sources that match those details. It then gives one of three verdicts: • Found — a name, with a quote from a cited source that supports it, so you can check the match yourself. • Leads — a short list of leads to check, when the sources point somewhere but don't confirm every detail. • Not reachable — SF's search reached nothing. That's not a claim the thing can't be found. Your agent then knows whether to answer, keep looking, or say it can't place it, instead of guessing.

How to connect

  1. Claude: Open the Search Fragments listing in the Claude connectors directory and choose Connect. Claude listing Search Fragments exposes 4 tools here.

Tools

gate_probe

Claude
The gate before your agent answers. Call this FIRST for any question, before spending effort: one cheap look returns a routing verdict in a few seconds. - QUICK_LOOKUP: one page names the answer, with a quote copied from that page. Check the quote, then answer. - NEEDS_FULL_JOB: worth a full search. Call resolve_fragment with the user's words. - NOT_WORTH_IT: SF's one look found no page naming an answer, so a full search is unlikely to pay off (about 1 in 10 of these is still findable). Tell the user you cannot place it rather than guessing. - PROBE_UNAVAILABLE: the look failed. Treat as NEEDS_FULL_JOB. Every outcome is a routing estimate about SF's own look, never a claim that the thing cannot be found.

resolve_fragment

Claude
Resolves a half-remembered description of a book, film, song, artwork, person, or event that someone knows exists but can't name. Input reads like a memory ("there's this thing where...", "...somebody who...", "...a story about...") rather than a lookup. Matches this shape: - 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 this shape: - 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 Latency: calls typically take 10–20 seconds. Results are decide-by-eye, not asserted fact: a resolved title with a confidence level, a ranked shortlist of sources to check, or an explicit "not resolvable". Low-confidence findings are surfaced for a human to verify, not claimed as settled. Each result includes a resolution_id that identifies the stored resolution.

submit_resolution_feedback

Claude
Records accepted, partial or rejected feedback for a resolution_id returned by resolve_fragment in this session. accepted means the result is what the user meant; partial means it helped but is not quite it; rejected means it is not what the user meant. corrected_target and new_clue are optional and are stored as feedback only; they never change graph facts.

verify_claim

Claude
Checks whether current web sources support a specific factual assertion. Takes a claim as a natural-language statement; returns a verdict with cited evidence and stated limits. Verdict set: - "supported" — multiple independent sources directly confirm the specific claimed detail - "partially_supported" — sources confirm the entity and domain; specific detail is pointed to 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 All verdicts are DECIDE-BY-EYE. A "supported" verdict means current web sources confirm it — not that it is true. Evidence may be incomplete, biased, or outdated. The stated_limits field is always present and identifies what the evidence cannot confirm. Good input shape (specific, checkable assertions): - "Werner Herzog dragged a full-size steamship over a hill during the filming of Fitzcarraldo" - "Glenn Gould stopped giving live concerts in 1964" - "The Backrooms photograph originated on 4chan" Checks one specific factual statement. Not for identifying half-remembered works. Not this shape: - "there's a documentary about a filmmaker dragging a boat over a mountain" - "a musician famous for stopping performing"

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/search-fragments"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/search-fragments)