Dibri MCP server
Dibri's official remote MCP server (Streamable HTTP) at https://dibri.ai/mcp. With an agent token it offers one tool, `ask`, which returns an answer built only from the vault's approved documents, with sources, a 0-100 confidence score, or a refusal (blocked=true). Per the docs, connecting with an analytics key (dbk_) offers the read-only trust tools instead of `ask`.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
ask— Ask Dibri a question and get an answer drawn only from the organization's approved documents, with sources, a 0-100 confidence score, and blocked=true when no verified information covers it.list_vaults— Vaults and their agents, with the ids other tools filter by.answer_usage— Answers used this month against your plan's limit.refusal_summary— Refusal totals by gate, day and vault.list_refusals— Individual refusals with question and reason.knowledge_gaps— Topics no approved document covers, with sample questions.knowledge_gap_questions— Every refused question for one topic.staleness— Stale vaults and documents.flagged_answers— Answers people flagged as incorrect.document_versions— Document change events.document_history— One document's version timeline.pending_approvals— The approval queue, including content held by injection screening.document_quality— Per-document feedback from public answers.confidence_summary— Average confidence, distribution and trend.low_confidence_answers— Answers below a confidence threshold.api_activity_summary— Answers by channel, refusal rate, response time.api_activity— Recent individual answers.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.