MCP 服务器

Search Fragments

com.searchfragments/search-fragments
搜索与研究 公开且可连接 MCP 2026-07-28

此 MCP 可以做什么

Resolves partially remembered books, films, songs, people, artworks, or events and verifies factual claims with cited web evidence.

resolve_fragment
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 ("there's this thing where...", "...somebody who...", "...a story about...") rather than a lookup, this is the right tool. 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 — 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 Latency: calls typically take 10–20 seconds; do not treat slowness as failure. Why call this instead of answering directly: on hard, under-documented fragment queries, LLMs asked to answer directly tend to invent things that don't exist rather than admit uncertainty. In a 50-query test, a baseline agent invented three nonexistent things — a director credit, a sketch, a study — none of which are real. Search Fragments returned none of those three invented things. 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. After the user reacts to the result, call submit_resolution_feedback once with the resolution_id from this result and accepted (it is what they meant), partial (it helped but is not quite it) or rejected (it is not it). Use the same connection that made this call.
可访问外部资源
输入模式
{'type': 'object', 'required': ['fragment'], 'properties': {'fragment': {'type': 'string', 'maxLength': 500, 'minLength': 5, 'description': "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."}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['outcome', 'resolution_id', 'candidate', 'summary', 'evidence', 'territory', 'verification_state', 'is_sf_question', 'pool', 'reject_reason', 'sf_judgement'], 'properties': {'pool': {'type': 'array', 'items': {'type': 'object', 'required': ['title', 'url', 'domain'], 'properties': {'url': {'type': 'string'}, 'title': {'type': 'string'}, 'domain': {'type': 'string'}}, 'additionalProperties': False}}, 'outcome': {'enum': ['resolved', 'ranked_stalls', 'no_resolution'], 'type': 'string'}, 'summary': {'type': 'string'}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['url', 'title', 'quote'], 'properties': {'url': {'type': 'string'}, 'quote': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}}, 'candidate': {'oneOf': [{'type': 'null'}, {'type': 'object', 'required': ['title', 'creator', 'confidence'], 'properties': {'title': {'type': 'string'}, 'creator': {'type': ['string', 'null']}, 'snippet': {'anyOf': [{'type': 'null'}, {'type': 'object', 'required': ['text', 'url', 'title'], 'properties': {'url': {'type': 'string'}, 'text': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}], 'description': 'Optional verbatim excerpt from a fetched text source, for display. Null when no readable source text was retrieved. Not a model summary.'}, 'confidence': {'enum': ['high'], 'type': 'string'}}, 'additionalProperties': False}]}, 'territory': {'type': 'array', 'items': {'type': 'object', 'required': ['title', 'reason', 'evidence', 'unresolved'], 'properties': {'title': {'type': 'string'}, 'reason': {'type': 'string'}, 'snippet': {'anyOf': [{'type': 'null'}, {'type': 'object', 'required': ['text', 'url', 'title'], 'properties': {'url': {'type': 'string'}, 'text': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}], 'description': 'Optional verbatim excerpt from a fetched text source for this lead. Null when no readable source text was retrieved. Not a model summary.'}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['url', 'title', 'quote'], 'properties': {'url': {'type': 'string'}, 'quote': {'type': 'string'}, 'title': {'type': 'string'}}, 'additionalProperties': False}}, 'unresolved': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}}, 'sf_judgement': {'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}, 'reject_reason': {'type': ['string', 'null']}, 'resolution_id': {'type': ['number', 'null'], 'description': 'Stable ID for this resolution. Pass it to submit_resolution_feedback after the user recognises, rejects, or partially recognises the result.'}, 'is_sf_question': {'type': 'boolean'}, 'verification_state': {'enum': ['SUPPORTED_RELATION', 'PARTIAL_EVIDENCE', 'INSUFFICIENT_EVIDENCE', 'VERIFICATION_FAILED'], 'type': 'string'}}, 'additionalProperties': False}
submit_resolution_feedback
Submit Resolution Feedback
Attach human/agent recognition feedback to a prior resolve_fragment result. Use the resolution_id returned by resolve_fragment. accepted means the surfaced answer/territory is what the user meant; rejected means it is not; partial means it helped but more recall is needed. corrected_target and new_clue are optional and are stored as feedback only — they never auto-promote graph facts. Call it once per result, from the same connection (same token, or same MCP session for anonymous access) that made the resolve_fragment call. Do not include personal data.
输入模式
{'type': 'object', 'required': ['resolution_id', 'status'], 'properties': {'note': {'type': ['string', 'null'], 'description': 'Optional free-text note. Max 1000 characters. No personal data.'}, 'status': {'enum': ['accepted', 'rejected', 'partial'], 'type': 'string', 'description': 'accepted: the result is what the user meant. partial: it helped but is not quite it. rejected: it is not what the user meant.'}, 'new_clue': {'type': ['string', 'null'], 'description': 'Optional. An extra detail the user remembered after seeing the result. Max 500 characters.'}, 'resolution_id': {'type': 'number', 'description': 'The resolution_id returned by the resolve_fragment call this feedback is about.'}, 'corrected_target': {'type': ['string', 'null'], 'description': 'Optional. What the user was actually thinking of, if they know it. Max 300 characters.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['recorded', 'resolution_id', 'status'], 'properties': {'status': {'enum': ['accepted', 'rejected', 'partial'], 'type': 'string'}, 'recorded': {'type': 'boolean'}, 'resolution_id': {'type': 'number'}}, 'additionalProperties': False}
verify_claim
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: - "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" Not this shape — these need resolve_fragment instead: - "there's a documentary about a filmmaker dragging a boat over a mountain" - "a musician famous for stopping performing"
可访问外部资源 幂等
输入模式
{'type': 'object', 'required': ['claim'], 'properties': {'claim': {'type': 'string', 'maxLength': 500, 'minLength': 5, 'description': 'A specific factual assertion to check against current web sources. Should be a concrete, checkable statement — not a question or a half-remembered fragment.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['verdict', 'evidence', 'stated_limits'], 'properties': {'verdict': {'enum': ['supported', 'partially_supported', 'unsupported', 'insufficient_evidence'], 'type': 'string', 'description': "'supported' = multiple independent sources directly confirm the specific claimed detail. 'partially_supported' = sources confirm entity + domain; detail pointed to but not directly stated. 'unsupported' = a credible source explicitly contradicts the claim. 'insufficient_evidence' = pool doesn't address the specific claim; fires freely."}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'properties': {'url': {'type': 'string'}, 'title': {'type': 'string'}, 'domain': {'type': 'string'}}}, 'description': 'Web sources retrieved. Always DECIDE-BY-EYE — human must verify before acting.'}, 'stated_limits': {'type': 'string', 'description': 'What the evidence cannot confirm, even when verdict is supported. Always present.'}}}
已更改
verify_claim
2026年10月1日 02:54
已更改
submit_resolution_feedback
2026年10月1日 02:54
已更改
resolve_fragment
2026年10月1日 02:54
已更改
resolve_fragment
2026年9月29日 03:03
已更改
resolve_fragment
2026年9月27日 02:53
已添加
submit_resolution_feedback
2026年9月21日 03:01
已更改
resolve_fragment
2026年9月21日 03:01
已更改
resolve_fragment
2026年9月19日 02:52
已添加
verify_claim
2026年9月17日 12:37
已添加
resolve_fragment
2026年9月17日 12:37