US Brand Intelligence MCP server
com.timzinin.api/us-brand-intelligenceapi.timzinin.comstreamable-httpv1.0.0Scanned
Pay-per-call US brand evidence and signal workflows with free MCP discovery and x402 payments.
21 tools: 1 do something that can't be undone, 16 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 18
- Can send data out · 0
- 7 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 US Brand Intelligence MCP server can do
The US Brand Intelligence MCP server is published by api.timzinin.com, a domain the MCP Registry verified. It has 21 tools. It can do things that cannot be undone, such as sending, paying or publishing (us-brand-signal-merge-report) and create or change data (16 tools: pricing_info, us-brand-action-queue, us-brand-evidence-chronology-builder, us-brand-evidence-citation-table and 12 more), but cannot delete data. 4 tools only read.
18 tools bring in text other people can write (us-brand-action-queue, us-brand-evidence-chronology-builder, us-brand-evidence-citation-table and 15 more).
The fixed checks matched 7 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 2026, version 1.0.0.
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.
21 tools
Can't be undone 1Claude Code: ask
us-brand-signal-merge-reportReconcile two buyer-supplied batches of normalized US brand signals.Reads text others write3 findings
Why it is in this group
- The name "us-brand-signal-merge-report" says "merge": a word for a change that another call does not undo.
- 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.
Findings
- Info
The input schema at properties.left.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.left.items.properties.sourceUrl.description: "...d HTTPS provenance URL; runtime rejects credentials, fragments, bracketed hosts, and non-de..."
- Info
The input schema at properties.right.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.right.items.properties.sourceUrl.description: "...d HTTPS provenance URL; runtime rejects credentials, fragments, bracketed hosts, and non-de..."
- Warn
The server marks "us-brand-signal-merge-report" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "us-brand-signal-merge-report" says "merge": a word for a change that another call does not undo.
Description, as the server wrote it Reconcile two buyer-supplied batches of normalized US brand signals. Receive a deterministic union, exact duplicate IDs, field conflicts, one-sided ID sets, counts, and digests without choosing a winner or making a truth claim. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Merge Report
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
Changes things 16Claude Code: ask
pricing_infoFree — list every paid tool in the 'us-brand-intelligence' bundle with its price, payTo address and network.No 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.
Description, as the server wrote it Free — list every paid tool in the 'us-brand-intelligence' bundle with its price, payTo address and network. Call this first if you don't have a wallet ready yet.
Annotations the server declares
- title: Pricing — US Brand Intelligence
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
us-brand-action-queueTurn verified US brand signals into one deterministic prioritized action queue with evidence, urgency, ownership status, and rule traces for downstream operators and agents.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.
- 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.
Description, as the server wrote it Turn verified US brand signals into one deterministic prioritized action queue with evidence, urgency, ownership status, and rule traces for downstream operators and agents. The Actor does not send messages or write to destinations. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Action Queue
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-evidence-chronology-builderBuild a deterministic chronology from 1 to 30 closed US brand evidence rows and an explicit UTC as-of time.Reads text others write1 finding
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.
Findings
- Info
The input schema at properties.rows.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.rows.items.properties.sourceUrl.description: "...HTTPS URL with a non-empty host and no credentials; the Actor does not fetch or verify it."
Description, as the server wrote it Build a deterministic chronology from 1 to 30 closed US brand evidence rows and an explicit UTC as-of time. It sorts supplied facts, marks same-time groups, reports future-dated IDs, and emits stable counts and digests. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Evidence Chronology Builder
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-evidence-citation-tableTurn a small buyer-owned evidence packet into a stable citation table with bounded Markdown citations, host and source counts, limitations, and digests.Reads text others write1 finding
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.
Findings
- Info
The input schema at properties.rows.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.rows.description: "...UTC; source URLs must be HTTPS without credentials or fragments."
Description, as the server wrote it Turn a small buyer-owned evidence packet into a stable citation table with bounded Markdown citations, host and source counts, limitations, and digests. It formats the supplied facts and does not browse, fetch, verify, rank, or enrich them. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Evidence Citation Table
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-offer-evidence-normalizerTurn supplied US brand offer, coupon, ad, and landing-page evidence into closed deterministic JSON.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.
- 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.
Description, as the server wrote it Turn supplied US brand offer, coupon, ad, and landing-page evidence into closed deterministic JSON. Submit bounded inline rows or one authorized read-only Dataset; the Actor validates source proof and terms without browsing or inferring ownership. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Offer Evidence Normalizer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-batch-splitterSplit a bounded batch of normalized US brand signal rows by brand, event type, severity, or analysis status.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.
- 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.
Description, as the server wrote it Split a bounded batch of normalized US brand signal rows by brand, event type, severity, or analysis status. Receive stable groups, exact IDs, counts, and SHA-256 digests without browsing, enrichment, inference, or child calls. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Batch Splitter
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-brief-composerTurn a buyer-supplied snapshot of US brand signals into one bounded deterministic machine-readable brief.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.
- 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.
Description, as the server wrote it Turn a buyer-supplied snapshot of US brand signals into one bounded deterministic machine-readable brief. It reduces the facts you provide and does not discover, fetch, verify, or enrich evidence. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Brief Composer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-confidence-gateClassify buyer-supplied normalized US brand signal scores against explicit accept and review thresholds.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.
- 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.
Description, as the server wrote it Classify buyer-supplied normalized US brand signal scores against explicit accept and review thresholds. Receive sorted accepted, review, and rejected IDs with stable reason codes, counts, and digests; no source or identity claims are made. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Confidence Gate
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-cooccurrence-analyzerMeasure how often buyer-supplied opaque signal IDs appear together in bounded observation groups.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.
- 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.
Description, as the server wrote it Measure how often buyer-supplied opaque signal IDs appear together in bounded observation groups. Return stable signal counts, unordered pair counts, support, Jaccard overlap, and digests without fetching or making causality claims. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Co-occurrence Analyzer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-crm-field-mapperTurn 1 to 100 buyer-supplied US brand signal rows into unsent HubSpot, Salesforce, or generic CRM field proposals while preserving evidence IDs and URLs.Reads text others write1 finding
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.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...reserving evidence IDs and URLs. No CRM credentials, network calls, proxy, LLM, identity re..."
Description, as the server wrote it Turn 1 to 100 buyer-supplied US brand signal rows into unsent HubSpot, Salesforce, or generic CRM field proposals while preserving evidence IDs and URLs. No CRM credentials, network calls, proxy, LLM, identity resolution, or arbitrary expressions. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal CRM Field Mapper
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-cross-tabulatorBuild a deterministic two-dimensional count table from buyer-supplied opaque rows, such as event type by status or brand by review state.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.
- 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.
Description, as the server wrote it Build a deterministic two-dimensional count table from buyer-supplied opaque rows, such as event type by status or brand by review state. It only counts the bounded request and does not verify sources or infer causality. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Cross-Tabulator
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-metrics-aggregatorCompute deterministic machine-friendly metrics for US brand signal rows you already collected, including event, severity, status, source, confidence, warning, and digest metrics.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.
- 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.
Description, as the server wrote it Compute deterministic machine-friendly metrics for US brand signal rows you already collected, including event, severity, status, source, confidence, warning, and digest metrics. Stateless, keyless, offline, and bounded for agent pipelines. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Metrics Aggregator
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-rule-routerTurn normalized US brand signals and ordered rules into a deterministic routing plan with matched routes, unmatched IDs, counts, warnings, and reproducible digests.No 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.
Description, as the server wrote it Turn normalized US brand signals and ordered rules into a deterministic routing plan with matched routes, unmatched IDs, counts, warnings, and reproducible digests. It never sends messages, calls destinations, fetches URLs, or infers identity. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Rule Router
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
us-brand-signal-sequence-transition-analyzerMeasure ordered adjacent transitions in buyer-supplied opaque sequences for workflow, funnel, and journey analysis.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.
- 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.
Description, as the server wrote it Measure ordered adjacent transitions in buyer-supplied opaque sequences for workflow, funnel, and journey analysis. The bounded processor analyzes only the JSON you provide and makes no identity or causality claim. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Sequence Transition Analyzer
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-sla-checkerClassify buyer-supplied schedule rows against an explicit UTC timestamp: which items met their due time, missed it, or remain open.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.
- 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.
Description, as the server wrote it Classify buyer-supplied schedule rows against an explicit UTC timestamp: which items met their due time, missed it, or remain open. Deterministic and offline; it never fetches a clock or resolves an item to a person or company. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal SLA Checker
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-webhook-payload-builderBuild one bounded deterministic unsent payload shaped for Slack, Teams, or a generic webhook from one normalized signal and buyer-supplied evidence.1 finding
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.
Findings
- Info
The input schema at properties.signal.properties.evidence.items.properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.signal.properties.evidence.items.properties.url.description: "HTTPS attribution URL without credentials or a non-default port."
Description, as the server wrote it Build one bounded deterministic unsent payload shaped for Slack, Teams, or a generic webhook from one normalized signal and buyer-supplied evidence. The Actor never sends a webhook or accepts a destination. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Webhook Payload Builder
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 4Show 4 read-only tools
us-brand-evidence-snapshot-diffCompare two small buyer-supplied US brand evidence snapshots and return a stable machine-readable report of added, removed, changed, and unchanged records.Reads text others writeNo findings
Why it is in this group
- The name "us-brand-evidence-snapshot-diff" says "snapshot": a word for reading.
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 Compare two small buyer-supplied US brand evidence snapshots and return a stable machine-readable report of added, removed, changed, and unchanged records. Inline-only, deterministic, and designed for agents that already own both snapshots. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Evidence Snapshot Diff
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-federal-award-snapshotGiven one exact USAspending recipient ID and a bounded UTC date window, return a deterministic snapshot of federal contract transactions for that recipient.Reads text others writeNo findings
Why it is in this group
- The name "us-brand-federal-award-snapshot" says "snapshot": a word for reading.
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 Given one exact USAspending recipient ID and a bounded UTC date window, return a deterministic snapshot of federal contract transactions for that recipient. Built for company and government-intelligence agents; no buyer URL, API key, browser, or LLM. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Federal Award Snapshot
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-brand-summarySummarize 1 to 60 buyer-supplied normalized US brand signals for up to 15 explicit brands.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "summarize": a word for reading.
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 Summarize 1 to 60 buyer-supplied normalized US brand signals for up to 15 explicit brands. Receive deterministic counts and grouped facts without identity resolution, source verification, browsing, or live enrichment. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Brand Summary
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
us-brand-signal-policy-simulatorCompare buyer-defined threshold policies over the same opaque US brand signal scores.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
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 Compare buyer-defined threshold policies over the same opaque US brand signal scores. Return accepted, review, and rejected IDs for every policy plus differences and sensitivity summaries; it does not choose or recommend a policy. — $0.05/call, x402 (USDC on base).
Annotations the server declares
- title: US Brand Signal Policy Simulator
- readOnlyHint: true
- destructiveHint: false
- 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 write18
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- us-brand-action-queue
- us-brand-evidence-chronology-builder
- us-brand-evidence-citation-table
- us-brand-evidence-snapshot-diff
- us-brand-federal-award-snapshot
- us-brand-offer-evidence-normalizer
- us-brand-signal-batch-splitter
- us-brand-signal-brand-summary
- us-brand-signal-brief-composer
- us-brand-signal-confidence-gate
- us-brand-signal-cooccurrence-analyzer
- us-brand-signal-crm-field-mapper
- and 6 more
- 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, 19:26 UTC, unchanged since Oct 22, 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
- 17
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 17 tools that change things (1 irreversible, 16 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.timzinin.com/mcp/us-brand-intelligence: tools/list returned 21 tools to an anonymous client, including us-brand-signal-merge-report (irreversible), pricing_info (write), us-brand-action-queue (write), us-brand-evidence-chronology-builder (write), us-brand-evidence-citation-table (write) and 12 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "us-brand-signal-merge-report" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "us-brand-signal-merge-report" says "merge": a word for a change that another call does not undo.
The input schema at properties.rows.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.rows.items.properties.sourceUrl.description: "...HTTPS URL with a non-empty host and no credentials; the Actor does not fetch or verify it."
The input schema at properties.rows.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.rows.description: "...UTC; source URLs must be HTTPS without credentials or fragments."
The description mentions "credentials".
What this check looks forMatched text
description: "...reserving evidence IDs and URLs. No CRM credentials, network calls, proxy, LLM, identity re..."
The input schema at properties.left.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.left.items.properties.sourceUrl.description: "...d HTTPS provenance URL; runtime rejects credentials, fragments, bracketed hosts, and non-de..."
The input schema at properties.right.items.properties.sourceUrl.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.right.items.properties.sourceUrl.description: "...d HTTPS provenance URL; runtime rejects credentials, fragments, bracketed hosts, and non-de..."
Show 1 more findingShow fewer
The input schema at properties.signal.properties.evidence.items.properties.url.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.signal.properties.evidence.items.properties.url.description: "HTTPS attribution URL without credentials or a non-default port."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http us-brand-intelligence https://api.timzinin.com/mcp/us-brand-intelligenceclaude mcp add --transport http us-brand-intelligence https://api.timzinin.com/mcp/us-brand-intelligenceRun 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": [
"mcp__us-brand-intelligence__us-brand-evidence-snapshot-diff",
"mcp__us-brand-intelligence__us-brand-federal-award-snapshot",
"mcp__us-brand-intelligence__us-brand-signal-brand-summary",
"mcp__us-brand-intelligence__us-brand-signal-policy-simulator"
],
"ask": [
"mcp__us-brand-intelligence__pricing_info",
"mcp__us-brand-intelligence__us-brand-action-queue",
"mcp__us-brand-intelligence__us-brand-evidence-chronology-builder",
"mcp__us-brand-intelligence__us-brand-evidence-citation-table",
"mcp__us-brand-intelligence__us-brand-offer-evidence-normalizer",
"mcp__us-brand-intelligence__us-brand-signal-batch-splitter",
"mcp__us-brand-intelligence__us-brand-signal-brief-composer",
"mcp__us-brand-intelligence__us-brand-signal-confidence-gate",
"mcp__us-brand-intelligence__us-brand-signal-cooccurrence-analyzer",
"mcp__us-brand-intelligence__us-brand-signal-crm-field-mapper",
"mcp__us-brand-intelligence__us-brand-signal-cross-tabulator",
"mcp__us-brand-intelligence__us-brand-signal-merge-report",
"mcp__us-brand-intelligence__us-brand-signal-metrics-aggregator",
"mcp__us-brand-intelligence__us-brand-signal-rule-router",
"mcp__us-brand-intelligence__us-brand-signal-sequence-transition-analyzer",
"mcp__us-brand-intelligence__us-brand-signal-sla-checker",
"mcp__us-brand-intelligence__us-brand-signal-webhook-payload-builder"
],
"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 us-brand-intelligence. Review it before you use it.
Capability tags behind 18 rules
- mcp__us-brand-intelligence__us-brand-action-queue untrusted-input
- mcp__us-brand-intelligence__us-brand-evidence-chronology-builder untrusted-input
- mcp__us-brand-intelligence__us-brand-evidence-citation-table untrusted-input
- mcp__us-brand-intelligence__us-brand-evidence-snapshot-diff untrusted-input
- mcp__us-brand-intelligence__us-brand-federal-award-snapshot untrusted-input
- mcp__us-brand-intelligence__us-brand-offer-evidence-normalizer untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-batch-splitter untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-brand-summary untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-brief-composer untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-confidence-gate untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-cooccurrence-analyzer untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-crm-field-mapper untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-cross-tabulator untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-merge-report untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-metrics-aggregator untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-policy-simulator untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-sequence-transition-analyzer untrusted-input
- mcp__us-brand-intelligence__us-brand-signal-sla-checker 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.timzinin.api/us-brand-intelligence/verify?hash=b1da73145e55a208cc665e7a9faee2afb7f31b0e23d4aea7972a5addd9756316" | jq -e '.changed == false'Pinned hash b1da73145e55, from Nov 17, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.timzinin.api/us-brand-intelligence/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.timzinin.api/us-brand-intelligence)Source: MCP Registry. Synced Oct 21, 2026, 18:07 UTC.
US Brand Intelligence MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the US Brand Intelligence MCP server safe?
- No scan can promise that. What its definitions show: 21 tools, 17 of which can change, send or delete something, and 7 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 US Brand 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 US Brand Intelligence MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: us-brand-signal-merge-report.
What tools does the US Brand Intelligence MCP server have?
- 21 tools: 1 irreversible, 16 write, 4 read. us-brand-signal-merge-report, pricing_info, us-brand-action-queue, us-brand-evidence-chronology-builder, us-brand-evidence-citation-table, us-brand-offer-evidence-normalizer, us-brand-signal-batch-splitter, us-brand-signal-brief-composer and 13 more.
Does the US Brand Intelligence MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the US Brand Intelligence MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the US Brand Intelligence MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.