{
  "markdown": "<p>\n  <img src=\"assets/logo.png\" alt=\"BackEngine\" width=\"128\" height=\"128\">\n</p>\n\n<h1>BackEngine MCP Server</h1>\n\n<p>\n  The customer-context layer for your revenue team — available to Claude and any MCP client.\n</p>\n\n## What is BackEngine?\n\nBackEngine is a multi-tenant SaaS platform that ingests all of an organization's customer\nand prospect communications — Slack threads, emails, call and meeting transcripts, and support\ntickets — and distills them into structured, queryable context. Raw conversations are processed\ninto **signals** (categorized, attributed moments), **sources** (the underlying transcripts,\nemails, and tickets), and rolling **project overviews**, all isolated per tenant and scoped by\nrole and access controls. The MCP server exposes this layer over the\n[Model Context Protocol](https://modelcontextprotocol.io), so an LLM client can query customer\nsignals, reconstruct context, prep for meetings, surface at-risk accounts, and draft grounded\noutreach from real conversation history — without leaving the chat.\n\n## Connecting\n\nThe server is remote and speaks streamable HTTP at **`https://backengine-prod.backengine.ai/mcp`**. You'll\nneed a BackEngine account; the server authenticates your session on connect.\n\n### Clients with native remote MCP support\n\n```json\n{\n  \"mcpServers\": {\n    \"backengine\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://backengine-prod.backengine.ai/mcp\"\n    }\n  }\n}\n```\n\n### Clients that require a stdio bridge\n\nFor clients that don't yet support remote servers directly, proxy through\n[`mcp-remote`](https://www.npmjs.com/package/mcp-remote):\n\n```json\n{\n  \"mcpServers\": {\n    \"backengine\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https://backengine-prod.backengine.ai/mcp\"]\n    }\n  }\n}\n```\n\n## Tools\n\nThe core tools for querying customer and prospect context are listed below. The exact tool set\nis resolved per connection — additional tools (creating and updating records, and\nintegration-specific actions for Jira, Zendesk, HubSpot, Salesforce, and Slack) become available\nbased on your permissions and which integrations your workspace has connected.\n\n| Tool | Description |\n| --- | --- |\n| `list_projects` | List customers and prospects; filter by name, type, etc. |\n| `get_project` | Retrieve a customer or prospect, optionally with its overview. |\n| `get_project_overview` | Pre-computed rolling 12-week summary for a customer or prospect. |\n| `list_signals` | List signals (categorized moments); filter by project, role, and time. |\n| `find_similar_signals` | Semantic search across signals from a natural-language query. |\n| `list_sources` | List sources — transcripts, emails, Slack threads, and tickets. |\n| `get_source` | Retrieve a source's content (summary, verbatim, or metadata only). |\n| `list_roles` | List the perspective lenses (e.g. product, sales, CS) used to filter signals. |\n| `find_contacts` | Find contacts by name, email, job title, or project. |\n| `list_signal_speakers` | List who has been speaking across signals. |\n\n## Links\n\n- Website: https://backengine.ai\n- MCP endpoint: https://backengine-prod.backengine.ai/mcp\n- Model Context Protocol: https://modelcontextprotocol.io\n",
  "bytes": 3194,
  "sha": "c843f5ee4be73ea5af56823ef9a47ba138a8ffc27d665b11bd733d488b95e409",
  "repo_slug": "backengine-ai/backengine-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_backengine_backengine_mcp_5e109999/readme"
}