01
Choose an AI assistant
Use an MCP-compatible client that supports remote Streamable HTTP and OAuth discovery, or a manual bearer token when required.
AI assistant integration · Powered by MCP
Connect an MCP-compatible AI assistant to investigate findings, compare provider runs, retrieve retained evidence, and prepare an evidence-backed worklist using the structured records already held in your workspace.
Read-only · organisation-scoped · OAuth + PKCE · revocable access
Connected assistant
BrandPresence evidence workspace
The strongest current priorities are the critical crawl finding, the missing organisation schema on commercial pages, and the retained provider answer/source evidence attached to the question.
The workflow
01
Use an MCP-compatible client that supports remote Streamable HTTP and OAuth discovery, or a manual bearer token when required.
02
An owner or admin chooses the organisation and controls which read scopes the connection can use.
03
Investigate findings, monitoring runs, Answer Ledger entries, experiments, search performance, and usage without exporting the workspace first.
Questions to ask
Which critical findings should we fix first, and what evidence supports that order?
Where does Perplexity mention us while OpenAI and Gemini do not?
Explain the evidence behind the highest-priority observed gap.
What changed across our latest AI monitoring runs?
Which experiments are still waiting for after-change evidence?
Available evidence
The MCP surface retrieves approved evidence. It cannot edit a website, start monitoring, or mutate workspace data.
Connections inherit an explicit organisation boundary. Supplied site and entity identifiers are filters rather than authorization.
Compatible clients can discover authorization from the MCP endpoint. Manual scoped tokens remain available for clients that require custom headers.
Use the evidence beyond the dashboard
AI assistant access is included with BrandPresence monitoring plans and remains under organisation-owner control.