Search Fragments MCP server
com.searchfragments/search-fragmentssearchfragments.comstreamable-httpv0.2.7Scanned
The gate before your agent answers: a verdict on whether a half-remembered thing can be reached.
3 tools: 3 change things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Search Fragments MCP server can do
The Search Fragments MCP server is published by searchfragments.com, a domain the MCP Registry verified. It has 3 tools. It can create or change data (3 tools: resolve_fragment, submit_resolution_feedback and verify_claim), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (resolve_fragment and verify_claim).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 0.2.7.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 3Claude Code: ask
resolve_fragmentReturns a verdict first, so your agent knows whether to answer, keep looking or say it can't place it: ORIGIN_OF_TRUTH (found, evidence checked, with sources), PARTIAL_ORIGIN (lead…Reads text others write1 finding
Why it is in this group
- The name "resolve_fragment" says "resolve": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "resolve_fragment" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "resolve_fragment" says "resolve": a word for reading.
Description, as the server wrote it Returns a verdict first, so your agent knows whether to answer, keep looking or say it can't place it: ORIGIN_OF_TRUTH (found, evidence checked, with sources), PARTIAL_ORIGIN (leads to follow, not an answer) or NOT_REACHABLE (SF's search reached nothing; not a claim the thing can't be found). Pieces together the name of a film, TV or radio show, song, book, game, quote, person, place, event or research study from the fragments a user remembers: a scene, a line, a face, roughly when. Pass every fragment in the user's own words, even uncertain ones. It searches many sources and fits them together. A shortlist or an honest "can't place it" is still useful. Use it when your own search couldn't place it. Not for known titles, trivia, recommendations or checking claims (use verify_claim). When the user says whether this helped, report it with submit_resolution_feedback.
Annotations the server declares
- title: Resolve Fragment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
submit_resolution_feedbackAfter the user reacts to a resolve_fragment result, call this with its resolution_id.No findings
Why it is in this group
- The name "submit_resolution_feedback" says "submit": a word for a change.
Description, as the server wrote it After the user reacts to a resolve_fragment result, call this with its resolution_id. accepted: it is what they meant. partial: it helped but is not quite it. rejected: it is not what they meant. If they recognised an item in the shortlist or leads, send picked_rank (1 = first item) or picked_url; if nothing fitted, send none_fitted: true. corrected_target and new_clue are optional and are stored as feedback only; they never change graph facts.
Annotations the server declares
- title: Submit Resolution Feedback
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
verify_claimChecks whether current web sources support a specific factual assertion.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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"
Annotations the server declares
- title: Verify Claim
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:46 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-11-25
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://searchfragments.com/.well-known/oauth-protected-resource
- Authorization servers
- https://searchfragments.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://searchfragments.com/api/mcp: tools/list returned 4 tools to an anonymous client, including gate_probe (write), resolve_fragment (write), submit_resolution_feedback (write), verify_claim (write)
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 3 to 4
Findings
Matches of fixed checks, with the text they matched.
- Warnresolve_fragment
The server marks "resolve_fragment" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "resolve_fragment" says "resolve": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
- Tools that change things, listed without credentials: 3 to 4
Tools1 changed.~1 changedView diff
- Changed:resolve_fragmentChanges thingsdescription
Tools1 changed.~1 changedView diff
- Changed:verify_claimChanges thingsdescriptioninputSchema
Install
Pinned to version 0.2.7. Values in angle brackets are yours to fill in.
claude mcp add --transport http search-fragments https://searchfragments.com/api/mcpclaude mcp add --transport http search-fragments https://searchfragments.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__search-fragments__resolve_fragment",
"mcp__search-fragments__submit_resolution_feedback",
"mcp__search-fragments__verify_claim"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as search-fragments. Review it before you use it.
Capability tags behind 2 rules
- mcp__search-fragments__resolve_fragment untrusted-input
- mcp__search-fragments__verify_claim untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.searchfragments/search-fragments/verify?hash=02677c0a8b564f406b138e1fa70bd8b1f8931ced17159da2242e6e8fb6998442" | jq -e '.changed == false'Pinned hash 02677c0a8b56, from Nov 12, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.searchfragments/search-fragments/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.searchfragments/search-fragments)Source: MCP Registry · repository. Synced Nov 12, 2026, 13:17 UTC.
Search Fragments MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Search Fragments MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Search Fragments MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Search Fragments MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Search Fragments MCP server have?
- 3 tools: 3 write. resolve_fragment, submit_resolution_feedback and verify_claim.
Does the Search Fragments MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Search Fragments MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Search Fragments MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.