ai.backengine/backengine-mcp
Surface customer & prospect context from Slack, email, transcripts and tickets in any MCP client.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
claude mcp add --transport http backengine-mcp 'https://backengine-prod.backengine.ai/mcp'
{
"mcpServers": {
"backengine-mcp": {
"type": "http",
"url": "https://backengine-prod.backengine.ai/mcp"
}
}
}
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
BackEngine MCP Server
The customer-context layer for your revenue team — available to Claude and any MCP client.
What is BackEngine?
BackEngine is a multi-tenant SaaS platform that ingests all of an organization's customer and prospect communications — Slack threads, emails, call and meeting transcripts, and support tickets — and distills them into structured, queryable context. Raw conversations are processed into signals (categorized, attributed moments), sources (the underlying transcripts, emails, and tickets), and rolling project overviews, all isolated per tenant and scoped by role and access controls. The MCP server exposes this layer over the Model Context Protocol, so an LLM client can query customer signals, reconstruct context, prep for meetings, surface at-risk accounts, and draft grounded outreach from real conversation history — without leaving the chat.
Connecting
The server is remote and speaks streamable HTTP at https://backengine-prod.backengine.ai/mcp. You'll
need a BackEngine account; the server authenticates your session on connect.
Clients with native remote MCP support
{
"mcpServers": {
"backengine": {
"type": "streamable-http",
"url": "https://backengine-prod.backengine.ai/mcp"
}
}
}
Clients that require a stdio bridge
For clients that don't yet support remote servers directly, proxy through
mcp-remote:
{
"mcpServers": {
"backengine": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://backengine-prod.backengine.ai/mcp"]
}
}
}
Tools
The core tools for querying customer and prospect context are listed below. The exact tool set is resolved per connection — additional tools (creating and updating records, and integration-specific actions for Jira, Zendesk, HubSpot, Salesforce, and Slack) become available based on your permissions and which integrations your workspace has connected.
| Tool | Description |
|---|---|
list_projects | List customers and prospects; filter by name, type, etc. |
get_project | Retrieve a customer or prospect, optionally with its overview. |
get_project_overview | Pre-computed rolling 12-week summary for a customer or prospect. |
list_signals | List signals (categorized moments); filter by project, role, and time. |
find_similar_signals | Semantic search across signals from a natural-language query. |
list_sources | List sources — transcripts, emails, Slack threads, and tickets. |
get_source | Retrieve a source's content (summary, verbatim, or metadata only). |
list_roles | List the perspective lenses (e.g. product, sales, CS) used to filter signals. |
find_contacts | Find contacts by name, email, job title, or project. |
list_signal_speakers | List who has been speaking across signals. |
Links
- Website: https://backengine.ai
- MCP endpoint: https://backengine-prod.backengine.ai/mcp
- Model Context Protocol: https://modelcontextprotocol.io
Questions fréquentes
Qu'est-ce que ai.backengine/backengine-mcp ?
Surface customer & prospect context from Slack, email, transcripts and tickets in any MCP client.
Comment installer ai.backengine/backengine-mcp ?
Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http backengine-mcp 'https://backengine-prod.backengine.ai/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour ai.backengine/backengine-mcp ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
ai.backengine/backengine-mcp est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient ai.backengine/backengine-mcp ?
Il est publié par BackEngine-ai. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.