Query the estate
Mentions, volume, sentiment, topics, and aggregates across projects, filtered by your taxonomy, returned as visual reports.
Brandwatch connector
Brandwatch MCP Connector – Mentions, Sentiment and Trends in Plain English
Brandwatch hears everything: the mentions, the sentiment, the topics gathering around your brand and your rivals. The problem was never the listening. It was that the hearing happened inside one analyst's dashboard, on the days that analyst had time.
The Brandwatch connector moves the hearing into the conversation. It links the AI you already use, like Claude, ChatGPT, or Copilot, to your Brandwatch Consumer Research projects through Mad Fish Elements. Your AI reads your projects and queries, pulls mentions with their sentiment, trends volume and topics, and works with the tags, categories, rules, and signals your team has built, with the full Consumer Research API behind it. The intelligence you pay to gather starts arriving where decisions happen.
See it
What Your AI Can See
Connect your account, and your AI reads the research estate: the projects, the queries inside them, and the data those queries have been gathering. Mentions come back with their metadata and sentiment. Volume trends over any window. Topic and aggregate views show what the conversation clusters around. Your taxonomy travels too: the tags, categories, and rules your analysts built organize the answers here just as they do in the platform.
The standing questions become sentences. "How did mention volume and sentiment move this week, and what drove the spikes?" "What topics are rising around our category?" "How does our share of voice compare to the two competitors this quarter?" And the question listening exists for: "what is the conversation saying about the thing we just launched?"
Beside the rest of the Gateway, listening gains context: the sentiment dip and the campaign calendar, the topic surge and the search trends, in one answer.
Do it
What Your AI Can Do
The Brandwatch connector is intelligence-first, with the write surface where analysts actually want it:
Watch on cadence
The Monday listening brief, the launch-week pulse, the always-on spike alert framed as a scheduled question.
Maintain the taxonomy
Manage tags, categories, rules, and signals through the API, shown first, so the organizing layer keeps up with the conversation it organizes.
Full API reach
Any Consumer Research path routes through the passthrough: the aggregate endpoints, the specific slices, the odd request that used to mean a dashboard session.
Building new listening queries remains analyst craft; the connector operates and organizes the estate your team designs.
A working session
The Launch-Week Pulse
In practiceThe session listening was built for: the campaign launched Tuesday. Wednesday morning you ask, "Mention volume and sentiment since Tuesday, versus the prior week, with the top topics." Your AI returns the pulse: volume up threefold, sentiment holding, and one topic cluster forming around the pricing change. You ask, "Show me representative mentions from that cluster." A dozen appear; the concern is specific and answerable. Marketing drafts the response content that afternoon, two days before the cluster would have become the story. Listening did its job because the hearing finally kept pace.
The return
What You Get Back
Spikes with explanations
Volume moves arrive with the topics and mentions behind them, not as bare graphs.
Launch pulses on tap
The first-72-hours answer, on schedule, while response still shapes the story.
Competitive rhythm
Share of voice and sentiment against rivals as a standing brief instead of a quarterly deck.
An estate that stays organized
Tags and rules maintained conversationally, so the taxonomy ages well.
Use cases
One Conversation, Real Account Work
"Weekly listening brief: volume, sentiment, top topics, and notable mentions."Brandwatch
The Monday pulse as a visual report.
"What drove yesterday's mention spike?"Brandwatch
The explanation behind the graph, with representative mentions.
"Share of voice against our two main competitors this quarter."Brandwatch
The competitive standing, trended.
"Tag the mentions in this cluster as pricing-feedback."Brandwatch
The taxonomy maintained on approval.
"Is the sentiment dip related to the campaign flight dates?"Brandwatch · Meta
Listening beside the media calendar, one answer.
For in-house teams
Close the expectation gap
The listening investment stops bottlenecking on dashboard time. Comms gets the spike explanation, product gets the feedback clusters, and leadership gets the pulse, all as questions.
For marketing teamsFor agencies
Run the whole book
Listening is the insight layer clients love and analysts ration. Standing briefs across client projects, from one connection with per-client permission walls, turn the rationed thing into a deliverable rhythm.
For agenciesReports worth sharing
From Live Account to Clear Story
Ask in chat and share the dashboard without building exports or taking screenshots.
Listening Pulse
Volume, sentiment, topics, notable mentions. Built for Mondays and launch weeks.
Competitive Voice Board
Share of voice and sentiment against rivals. Built for the quarterly narrative.
Topic Radar
Rising clusters around brand and category. Built for comms and content planning.
The charts do the talking: line for volume and sentiment trends, bar for share of voice, and topic clusters as ranked lists rather than decorative clouds. And when your leaders or clients want these anytime, the Data Visualization add-on turns your reports into always-current dashboards they open from a link. Ask in chat. Share the dashboard.
The useful signals
The Numbers That Matter
Listening reads on a few core signals. Volume, trended: how much conversation, and when it spikes. Sentiment, beside it: the temperature of the talk. Topics: what the conversation clusters around, the layer where spikes get explained. Share of voice against rivals: your slice of the category's attention. And notable mentions: the specific posts that shape the rest. The habit: the weekly pulse in calm times, daily during launches, and the spike question whenever a graph jumps. Volume without topics is noise. Topics without mentions is theory. The three together, on schedule, are what listening was bought for. This connector just makes the together part automatic.
A practical start
Your First Week
Day one: connect the projects and take the pulse. "Volume and sentiment this week, versus last." Day two: read the topics. "What clusters are forming around the brand?" Pull representative mentions for the biggest one. Day three: check the rivals. "Share of voice against our two competitors this quarter." Day four: tune the taxonomy. Tag one new cluster so next week's answers arrive organized; day five: schedule the brief. "Monday mornings, send the listening pulse; during launches, daily." By Friday, the listening investment reports on a rhythm instead of on analyst availability, comms has seen one cluster form early enough to matter, and the taxonomy is one tag sharper. The platform was always hearing; now the hearing arrives where decisions happen.
Works best with
Build the Connected View
Pair Brandwatch with Meta and the ad platforms so sentiment moves can be read against flight dates. Add Search Console for the organic-interest echo of a conversation spike. Listening, media, and search demand together tell you whether a moment is noise or the story.
A closing thought on rhythm; listening fails two ways: too rare, and too raw. Quarterly decks arrive after the story ended; raw dashboards drown the signal in mentions. The fix is the middle: a weekly pulse, topics attached, mentions on request. Small, regular, explained; that cadence is what this connector automates. The analysts keep the craft; the calendar keeps the discipline; the brand keeps its early warnings.
Clear limits
What This Connector Will Not Do
It will not post, reply, or engage anywhere; it listens and organizes, and response stays with your comms flow. It will not manufacture sentiment; every reading comes from your queries' actual data and reconciles with the platform. It will not replace analyst judgment on ambiguous clusters; it surfaces and you interpret. And it will not read projects you did not connect.
Governance
Governed Access Your Whole Org Can Live With
Access is set per person, not per account, so Read seats see everything and change nothing while Write seats create and edit with your approval flow in front of every change. Delete access goes only to people you trust to clean up, and many teams start read-only, check answers against the platform, then widen access as the audit trail earns it.
You choose the level of human review and can change it at any time, while every action records what changed, when, and who approved it. Per-user access means Elements never stores your Brandwatch password, and your data is never harvested or resold.
Per-user accessRead / write / delete per seatFull audit trailApproval flow on every change
Setup
Setup Takes Minutes
- Start your trialCreate your Elements account and connect it to your AI.
- Link BrandwatchSign in through the secure connection screen and choose what to connect. No code and no engineers.
- Set permissionsDecide who can Read, who can Write, and who can Delete. Start conservative and widen as trust builds.
- Ask your first question"How did we do last month?" is a complete instruction.
Plans, account limits, and the multi-client Agency plan are on the pricing page .
FAQ
Brandwatch Connector Questions
Can it build new listening queries?
Query design remains analyst craft in the platform. The connector operates the estate: asks it questions, maintains its taxonomy, and delivers its answers where decisions happen.
How current is the data?
As current as your Brandwatch queries themselves; the connector reads live through the Consumer Research API at the moment you ask.
What does the taxonomy write access cover?
Tags, categories, rules, and signals: the organizing layer. Changes are shown first and audited, so the structure your analysts rely on evolves deliberately.
Will my AI change things without asking me?
No. Your AI acts only with the permissions you set, and changes follow the review level you choose. Read-only seats cannot change anything, because the approval flow is the product working as designed.
Which AI assistants can our team use?
Your team can use Claude, ChatGPT, and Microsoft Copilot, while other AI tools can likely connect when they support MCP, the open standard for linking AI assistants to outside tools.
Is my data used to train anything?
No. Your data stays yours, so nothing is harvested and nothing is resold.
Focus on the Strategy, Delegate the Launch
The teams winning with AI are not handing their accounts to a black box; they keep the strategy and delegate the hands-on-keyboard work, while approvals and an audit trail make it safe to move fast. Connect the account you already have through the Gateway and ask the question you would normally build a report to answer.
Your first 14 days are free. Add your card to start, and cancel before the trial ends to pay nothing.