Backengine MCP server

What it does

BackEngine surfaces customer and prospect context from Slack, email, transcripts, and support tickets through an MCP interface. It processes communications into queryable signals, sources, and project overviews, allowing revenue teams to access structured customer context directly in Claude and other MCP clients.

• Query customer signals and project overviews to prepare for sales or support meetings with grounded conversation history.
• Search across email, Slack, and transcript data semantically to find relevant moments and context for a specific customer or prospect.
• Identify at-risk accounts or surface outreach opportunities by filtering signals by role, time, and project.

Tools this server exposes

Tool	Does
list_projects	List customers and prospects with filtering by name, type, and other attributes.
get_project	Retrieve details about a customer or prospect, optionally including its overview.
get_project_overview	Retrieve a pre-computed rolling 12-week summary for a customer or prospect.
list_signals	List signals (categorized moments in conversations) with filtering by project, role, and time.
find_similar_signals	Perform semantic search across signals using natural-language queries.
list_sources	List sources including transcripts, emails, Slack threads, and support tickets.
get_source	Retrieve a source's content as summary, verbatim text, or metadata only.
list_roles	List the perspective lenses (such as product, sales, or customer success) used to filter signals.
find_contacts	Find contacts by name, email, job title, or associated project.
list_signal_speakers	List who has been speaking across signals.

Before you enable it

An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.

This server has not seen a commit in 2 mo. It may still work, but nobody is currently fixing it — check the alternatives before you build on it.