Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ai.nudg3/brand-intelligence

PYPI · NUDG3-MCP · 2 COMPONENTS · SCANNED SEP 20

Query your Nudg3 brand visibility across ChatGPT, Claude, Gemini, AI Overviews, and Perplexity.

−15 this week 58 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 32 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2574 tokens (~234/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the ai.nudg3/brand-intelligence MCP server?

ai.nudg3/brand-intelligence runs locally as a PyPI package, launched with uvx nudg3-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · nudg3-mcp

# add to Claude Code
claude mcp add ai-nudg3-brand-intelligence -- uvx nudg3-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "ai-nudg3-brand-intelligence": {
      "command": "uvx",
      "args": [
        "nudg3-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "ai-nudg3-brand-intelligence": {
      "command": "uvx",
      "args": [
        "nudg3-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add ai-nudg3-brand-intelligence -- uvx nudg3-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-nudg3-brand-intelligence": {
      "type": "local",
      "command": [
        "uvx",
        "nudg3-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add ai-nudg3-brand-intelligence --command uvx --arg nudg3-mcp
# ~/.hermes/config.yaml
mcp_servers:
  ai-nudg3-brand-intelligence:
    command: "uvx"
    args: ["nudg3-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "ai-nudg3-brand-intelligence": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "nudg3-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add ai-nudg3-brand-intelligence -t stdio -c uvx -a nudg3-mcp
// mcp.json
{
  "mcpServers": {
    "ai-nudg3-brand-intelligence": {
      "command": "uvx",
      "args": [
        "nudg3-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 13 Sept 26 +15
    • Malware scan: unverified → pass security
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −18
    • Malware scan: pass → unverified security
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/nudg3-mcp@1.1.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 32 packages
Packages resolved 32
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~2,206 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze_competitors ~193

Competitive landscape — how brands rank on discovery (unbranded) queries. Shows position rankings, visibility gaps, and which competitors are gaining or losing ground. "Discovery" means unbranded category queries where brands compete on relevance, not brand recognition (e.g., "best AI monitoring tools"). Negative-sentiment classifications in the ranking are guaranteed by v1.14 persistence guards to be grounded in >= 1 negative indicator phrase (no separate quality knob needed — the data layer enforces it).

NameTypeReqDescription
date_rangestring"7d", "30d", "90d", or "YYYY-MM-DD:YYYY-MM-DD"
providersFilter by AI provider names (e.g. ["ChatGPT", "Gemini"])
workspace_idOptional. UUID of the workspace to target. Required only for agency/company keys with more than one workspace accessible.

Structured output declared, but exposes no named fields.

No examples provided.

analyze_prompts ~285

Prompt-level performance grouped by funnel stage. Shows which tracking prompts perform best/worst for a specific brand. visibility_type controls the analysis scope: - "organic" (default): Discovery/unbranded prompts only — the true competitive metric. Branded prompts are excluded because they inflate scores artificially. - "branded": Research + purchase prompts — what AI says when asked about you by name. - "all": All prompts regardless of tagging. Funnel stages explained: - Discovery: unbranded category queries ("best AI monitoring tools") - Research: evaluation/comparison queries ("Nudg3 vs Semrush") - Purchase: buy-intent queries ("Nudg3 pricing")

NameTypeReqDescription
brand_idOptional. UUID of the brand to analyze. If omitted, the workspace's primary brand is auto-resolved — call this tool without brand_id when the user just asks about "our prompts" or "we" without naming…
date_rangestring"7d", "30d", "90d", or "YYYY-MM-DD:YYYY-MM-DD"
providersFilter by AI provider names
visibility_typestring"organic" (default), "branded", or "all"
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

analyze_responses ~314

Read what AI models actually say — provider-grouped response samples. Default mode groups AI responses by provider with truncated text, sentiment scores, brand mention patterns, and co-mention detection. When `group_by` is supplied, the tool returns a cross-tab aggregation instead — useful for "Coca-Cola visibility by sub-sector x engine" style questions in one call. Supported dimensions: "provider", "category" ("tag" is accepted as an alias for "category"). Note: the cross-tab is aggregated over a sample of up to 100 matching responses, not the full dataset (server-side full-population aggregation is a Phase 2 follow-up — the result includes `is_sample` and `warning` fields).

NameTypeReqDescription
date_rangestring"7d", "30d", "90d", or "YYYY-MM-DD:YYYY-MM-DD"
group_byOptional list of dimensions to cross-tab on. Examples: ["provider"], ["category"], ["category","provider"].
limitintegerMax responses for default (non-group_by) mode. Default 15, max 20. Ignored when group_by is set (sample is always sized at 100).
providersFilter by AI provider names (e.g. ["ChatGPT"])
tagsFilter by funnel stage (e.g. ["discovery"])
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

analyze_sources ~138

Citation source analysis — which websites AI models cite. Shows top cited domains, source type distribution (reference, social, news, review, commerce), content gaps (missing source types), and competitor domains appearing in your brand's AI responses.

NameTypeReqDescription
date_rangestring"7d", "30d", "90d", or "YYYY-MM-DD:YYYY-MM-DD"
providersFilter by AI provider names
tagsFilter by funnel stage (e.g. ["discovery", "research"])
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

export_data ~180

Export raw workspace data as CSV. Use this only when the user wants raw data for spreadsheets or BI tools. For analysis, use the investigation tools (get_overview, analyze_*) instead. Datasets: chat_responses, sources_citations, dashboard_graph, prompts_mentions. Requires the export:data scope (Professional tier or above).

NameTypeReqDescription
confirm_large_exportbooleanSet true to proceed with exports over 10,000 rows
datasetstringyesOne of: chat_responses, sources_citations, dashboard_graph, prompts_mentions
date_fromstringyesStart date (YYYY-MM-DD)
date_tostringyesEnd date (YYYY-MM-DD)
providersFilter by provider names
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

get_actions ~259

List or retrieve workspace actions derived from report insights. Actions are recommendations that have been created from AI-generated insights or manually. Each action tracks status, priority, owner team, and links back to the source report. Two modes: - List: returns paginated actions with filters (default) - Detail: pass action_id for full action with context and brief info Requires read:insights scope (Professional tier or above).

NameTypeReqDescription
action_idUUID of a specific action (returns full detail with context)
owner_teamFilter: "tech", "content", "marketing", or "leadership"
pageintegerPage number for list mode
per_pageintegerResults per page (max 50)
priorityFilter: "high", "medium", or "low"
recommendation_typeFilter: "opportunity", "threat", "quick_win", or "prompt_edit"
source_report_idFilter by originating report UUID
statusFilter: "pending", "in_progress", "ready", "completed", or "dismissed"
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

get_insights ~199

Get AI-generated actionable insights from a visibility report. Returns categorized recommendations: opportunities (gaps to exploit), threats (competitive risks), quick wins (low-effort improvements), provider strategies (per-AI-provider tactics), content recommendations (what to create), and prompt edit suggestions. Requires read:insights scope (Professional tier or above).

NameTypeReqDescription
categoryFilter by team: "tech", "content", "marketing", or "leadership"
priorityFilter by priority: "high", "medium", or "low"
report_idstringyesUUID of the report to get insights for (required)
typeFilter by category: "opportunities", "threats", "quick_wins", "provider_strategies", "content_recommendations", or "all"
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

get_metric_catalog ~44

Discover what data is available in this Nudg3 workspace. Returns available investigation tools, filters, and export datasets. No API call is made — this is a static catalog.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_overview ~192

Compact workspace health check — start here. Returns current visibility scores for all tracked brands (primary + competitors), 7-day and 30-day trends as single numbers (not raw time-series), top cited sources, anomaly alerts, and suggested next investigations with parameters. This is the first tool to call. Follow the suggested_investigations in the response to drill deeper into specific areas.

NameTypeReqDescription
date_rangestring"7d", "30d", "90d", or "YYYY-MM-DD:YYYY-MM-DD"
providersFilter by AI provider names (e.g. ["ChatGPT", "Gemini"])
workspace_idOptional. UUID of the workspace to target. Required only for agency/company-scoped keys that authorise more than one workspace — pass it from the list_workspaces response. For workspace-scoped keys (…

Structured output declared, but exposes no named fields.

No examples provided.

get_reports ~239

List or retrieve visibility audit reports. Reports contain point-in-time snapshots of brand visibility including scores, competitive position, executive summaries, and AI-generated insights. Three modes: - List: returns paginated report summaries (default) - Latest: set latest=True to get the most recent report - Detail: pass report_id for full report with optional insights Requires read:insights scope (Professional tier or above).

NameTypeReqDescription
end_dateFilter by report date (YYYY-MM-DD)
include_insightsbooleanEmbed AI insights in the report detail response
latestbooleanIf true, returns the most recent report
pageintegerPage number for list mode
per_pageintegerResults per page (max 50)
report_idUUID of a specific report (returns full detail)
report_typeFilter: "free_audit", "weekly_report", or "on_demand"
start_dateFilter by report date (YYYY-MM-DD)
workspace_idOptional. UUID of the workspace. Required only for agency/company keys with >1 workspace.

Structured output declared, but exposes no named fields.

No examples provided.

list_workspaces ~163

List the workspaces this API key can access. Two personas: - Workspace-scoped key (default for single-brand customers): returns a single-element list with the key's bound workspace. - Agency or company-scoped key (multi-client portfolio): returns every workspace nested under each company in the portfolio. Use this first when an agency user asks "which workspaces do I have?" or before drilling into a specific brand. When an agency key has more than one workspace, every other tool will ask you to specify ``workspace_id`` explicitly — the response from this tool is what you pick from. No arguments required. Returns the live response from GET /api/v1/workspaces verbatim (scope_level, agency, companies tree).

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the ai.nudg3/brand-intelligence MCP server?

ai.nudg3/brand-intelligence is an MCP server listed in the public MCP registry as ai.nudg3/brand-intelligence. Query your Nudg3 brand visibility across ChatGPT, Claude, Gemini, AI Overviews, and Perplexity. This page covers its PyPI package (nudg3-mcp).

Is the ai.nudg3/brand-intelligence MCP server safe to use?

ai.nudg3/brand-intelligence scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the ai.nudg3/brand-intelligence MCP server expose?

ai.nudg3/brand-intelligence exposes 11 tools: get_metric_catalog, list_workspaces, get_overview, analyze_competitors, analyze_prompts, and 6 more. Their descriptions and schemas cost roughly 2,206 tokens of context every time the server is loaded.

Is the ai.nudg3/brand-intelligence MCP server still maintained?

ai.nudg3/brand-intelligence is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.