Skip to content

BRAINIAC News Verification & Information Intelligence MCP server

software.brainiac/news-intelligencebrainiac.softwarestreamable-httpv1.0.1Scanned

Paid News Verification & Information Intelligence API via x402. Unpaid tool calls return 402.

10 tools: 8 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 8 write, 2 read.
  • Reads private data · 2
  • Reads text others write · 10
  • Can send data out · 10
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

8 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.
Govern this server →

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 BRAINIAC News Verification & Information Intelligence MCP server can do

The BRAINIAC News Verification & Information Intelligence MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 10 tools. It can create or change data (8 tools: news-intelligence_original-source-trace, news-intelligence_syndication-cluster, news-intelligence_claim-extract, news-intelligence_claim-source-match and 4 more), but cannot delete data. 2 tools only read.

2 tools read private data (news-intelligence_source-independence-analyze and news-intelligence_contradiction-detect); 10 tools bring in text other people can write (news-intelligence_original-source-trace, news-intelligence_syndication-cluster, news-intelligence_claim-extract and 7 more); 10 tools can send data out of your system (news-intelligence_original-source-trace, news-intelligence_syndication-cluster, news-intelligence_claim-extract and 7 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.0.1.

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.

10 tools

Changes things 8Claude Code: ask
  • news-intelligence_claim-extractExtract claim-like sentences and quotes from supplied article text using local heuristics.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Extract claim-like sentences and quotes from supplied article text using local heuristics. Price $0.04 USDC. POST /api/v1/news-intelligence/claim-extract. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Extract news claims
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_claim-source-matchMatch supplied or extracted claims to articles by text overlap.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Match supplied or extracted claims to articles by text overlap. Multiple outlets repeating a claim are not independent confirmation. Price $0.05 USDC. POST /api/v1/news-intelligence/claim-source-match. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Match claims to sources
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_correction-history-detectFlag correction, update, and retraction wording or updatedAt changes in supplied articles.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Flag correction, update, and retraction wording or updatedAt changes in supplied articles. Price $0.03 USDC. POST /api/v1/news-intelligence/correction-history-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect news correction history
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_country-event-monitorFilter supplied articles and events by country into a dated monitor list.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Filter supplied articles and events by country into a dated monitor list. Price $0.04 USDC. POST /api/v1/news-intelligence/country-event-monitor. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Monitor country news events
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_event-timeline-buildOrder supplied events or dated articles into a timeline without inventing missing dates.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Order supplied events or dated articles into a timeline without inventing missing dates. Price $0.04 USDC. POST /api/v1/news-intelligence/event-timeline-build. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Build news event timeline
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_original-source-traceCluster similar articles and identify the earliest published item.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Cluster similar articles and identify the earliest published item. Later reprints are not treated as independent confirmation. Price $0.05 USDC. POST /api/v1/news-intelligence/original-source-trace. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Trace original news sources
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_syndication-clusterGroup near-duplicate titles and bodies into syndication clusters without counting repeats as confirmation.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Group near-duplicate titles and bodies into syndication clusters without counting repeats as confirmation. Price $0.04 USDC. POST /api/v1/news-intelligence/syndication-cluster. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Cluster syndicated news articles
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_verification-evidence-reportAggregate source tracing, syndication, claims, contradictions, corrections, and independence findings.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Aggregate source tracing, syndication, claims, contradictions, corrections, and independence findings. Repeats are never independent confirmation. Price $0.08 USDC. POST /api/v1/news-intelligence/verification-evidence-report. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Build news verification evidence report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Show 2 read-only tools
  • news-intelligence_contradiction-detectFind affirming vs negating overlapping claims, and label near-duplicate repeats without treating them as confirmation.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Find affirming vs negating overlapping claims, and label near-duplicate repeats without treating them as confirmation. Price $0.05 USDC. POST /api/v1/news-intelligence/contradiction-detect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect news claim contradictions
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • news-intelligence_source-independence-analyzeCount distinct outlets and mark syndicated/similar copies as non-independent.Reads private dataReads text others writeCan send data outNo findings

    Why it is in this group

    • The name "news-intelligence_source-independence-analyze" says "analyze": a word for reading.

    What it can reach

    • private-dataThe input names a file (input.file), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.rss.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Count distinct outlets and mark syndicated/similar copies as non-independent. Repeats are never claimed as confirmation. Price $0.04 USDC. POST /api/v1/news-intelligence/source-independence-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyze news source independence
    • readOnlyHint: true
    • 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.

200 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 private-data tools breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__news-intelligence__news-intelligence_contradiction-detect",
      "mcp__news-intelligence__news-intelligence_source-independence-analyze"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:34 UTC, unchanged since Nov 20, 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
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.brainiac.software/mcp/news-intelligence: tools/list returned 10 tools to an anonymous client, including news-intelligence_original-source-trace (write), news-intelligence_syndication-cluster (write), news-intelligence_claim-extract (write), news-intelligence_claim-source-match (write), news-intelligence_event-timeline-build (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools10 changed.~10 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http news-intelligence https://www.brainiac.software/mcp/news-intelligence
claude mcp add --transport http news-intelligence https://www.brainiac.software/mcp/news-intelligence

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__news-intelligence__news-intelligence_original-source-trace",
      "mcp__news-intelligence__news-intelligence_syndication-cluster",
      "mcp__news-intelligence__news-intelligence_claim-extract",
      "mcp__news-intelligence__news-intelligence_claim-source-match",
      "mcp__news-intelligence__news-intelligence_event-timeline-build",
      "mcp__news-intelligence__news-intelligence_correction-history-detect",
      "mcp__news-intelligence__news-intelligence_source-independence-analyze",
      "mcp__news-intelligence__news-intelligence_contradiction-detect",
      "mcp__news-intelligence__news-intelligence_country-event-monitor",
      "mcp__news-intelligence__news-intelligence_verification-evidence-report"
    ],
    "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 news-intelligence. Review it before you use it.

Capability tags behind 10 rules
  • mcp__news-intelligence__news-intelligence_original-source-trace untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_syndication-cluster untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_claim-extract untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_claim-source-match untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_event-timeline-build untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_correction-history-detect untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_source-independence-analyze private-data, untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_contradiction-detect private-data, untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_country-event-monitor untrusted-input, outbound
  • mcp__news-intelligence__news-intelligence_verification-evidence-report untrusted-input, outbound

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/software.brainiac/news-intelligence/verify?hash=b37505c084991509581f918a8dfca5250f31845f3414f7a8cfce7c094681c646" | jq -e '.changed == false'

Pinned hash b37505c08499, from Nov 20, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/software.brainiac/news-intelligence/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for software.brainiac/news-intelligence
[![Anlyon Radar](https://radar.anlyon.com/badge/software.brainiac/news-intelligence.svg)](https://radar.anlyon.com/servers/software.brainiac/news-intelligence)

Source: MCP Registry. Synced Nov 20, 2026, 01:18 UTC.

BRAINIAC News Verification & Information Intelligence MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BRAINIAC News Verification & Information Intelligence MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 8 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the BRAINIAC News Verification & Information Intelligence MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BRAINIAC News Verification & Information Intelligence 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 BRAINIAC News Verification & Information Intelligence MCP server have?

10 tools: 8 write, 2 read. news-intelligence_original-source-trace, news-intelligence_syndication-cluster, news-intelligence_claim-extract, news-intelligence_claim-source-match, news-intelligence_event-timeline-build, news-intelligence_correction-history-detect, news-intelligence_country-event-monitor, news-intelligence_verification-evidence-report and 2 more.

Does the BRAINIAC News Verification & Information Intelligence MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BRAINIAC News Verification & Information Intelligence MCP server send data to outside services?

10 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): news-intelligence_original-source-trace, news-intelligence_syndication-cluster, news-intelligence_claim-extract, news-intelligence_claim-source-match, news-intelligence_event-timeline-build, news-intelligence_correction-history-detect and 4 more.

Has the BRAINIAC News Verification & Information Intelligence MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.