广告合作
MCP.so
登录

Quelvio MCP Server

@Quelvio

代码仓库主页

基本信息

分类

记忆与知识

许可证

MIT

传输方式

stdio

作者

Quelvio

提交者

Antonis Papathanasopoulos

关于 Quelvio MCP Server

Your company's brain for AI agents. MCP server for Quelvio enterprise knowledge platform.

#knowledge#search#enterprise#rag#oauth#streamable-http

Quelvio MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "quelvio": {
      "url": "https://mcp.quelvio.com/http",
      "transport": "streamable-http",
      "auth": "oauth2"
    }
  }
}

Quelvio MCP Server 工具

3

Search the company's connected knowledge across every source — Drive, SharePoint, Confluence, Slack, Notion — with cited synthesized answers, lifecycle awareness, and refusal-on-weak-context. Returns a written answer with [n] citations plus the ranked source chunks. Modes: `fast` (1,500 kT — retrieval-only, no synthesis), `standard` (12,500 kT — default; synthesized answer over the top retrieval set), `deep` (25,000 kT — wider retrieval + premium synthesis for complex questions). Pick the cheapest tier that answers the question. Responses are capped at 25,000 output tokens per Claude Connectors policy; if truncated, structured metadata carries `truncated: true` and `query_id` so the agent can call `get_source_detail` for full provenance.

List the taxonomy domains the company has indexed — with document counts, expert counts, and coverage levels — so an agent can decide whether to query before spending a Knowledge Token. Returns one row per domain with the canonical `taxonomy_domain` slug, document/chunk counts, expert count, coverage level (expert | partial | none), the single_expert risk flag, and the top contributor by authority. Use the slug as the `domain` filter on a follow-up `query_knowledge` call. Zero Knowledge Tokens consumed.

Return per-chunk source provenance for a previous query — document path, lifecycle state, embedding timestamp, contributor, last-updated — useful for verifying a citation or surfacing trust signals to a downstream system. Pass a `query_id` returned by an earlier `query_knowledge` call. Returns 404 if the query_id is unknown OR belongs to a different tenant (indistinguishable to prevent info-leak). Zero Knowledge Tokens consumed.

概览

What is Quelvio?

Quelvio is an MCP server that lets you search your company’s connected knowledge (from Drive, SharePoint, Confluence, Slack, Notion) directly from any AI tool supporting the Model Context Protocol. It is built for enterprise teams who want to query internal documents and conversations through assistants like Claude Desktop, Cursor, or VS Code Copilot.

How to use Quelvio?

Add the server’s URL (https://mcp.quelvio.com/http) to your MCP client’s configuration (JSON file or CLI). On first tool call, your browser opens your organization’s OAuth sign-in page; after signing in, the client resumes automatically. No API key is needed.

Key features of Quelvio

  • Search across Drive, SharePoint, Confluence, Slack, and Notion.
  • Three knowledge‑retrieval modes: fast, standard, deep.
  • Zero API key provisioning—OAuth sign‑in only.
  • Permission‑scoped to your individual employee identity.
  • Three‑layer access control: tenant, role, source ACLs.
  • Streamable HTTP transport with SSE synthesis streaming.

Use cases of Quelvio

  • Ask an AI assistant “What’s our deployment process for the payments service?” and get a synthesized answer with citations.
  • Before querying, discover which taxonomy domains have relevant knowledge using list_domains.
  • Verify a citation’s source document, lifecycle state, and contributor via get_source_detail.
  • Let team members search company knowledge from their preferred MCP‑compatible client without provisioning keys.

常见问题

1

How do I authenticate to Quelvio?

There is no API key. The first time you invoke a tool, your client redirects you to your organization’s Clerk‑hosted sign‑in page. After signing in, the client reuses the OAuth token (valid ~30 days).

2

What permissions apply when I query?

Every query is scoped to your individual identity. The server enforces tenant isolation, role‑based feature access (Owner/Admin/Member), and source‑system ACLs (e.g., Google Drive shares, SharePoint groups). You only see what your account would see in those source systems.

3

What does it cost to use the server?

Tool calls consume Knowledge Tokens (kT): `list_domains` and `get_source_detail` are free; `query_knowledge` costs 1,500 kT (fast), 12,500 kT (standard), or 25,000 kT (deep). These rates are locked at the v0.9 release.

4

Can I self-host the server?

Yes. The server runs on Cloudflare Workers. Use `wrangler` to deploy with a `TOKEN_ENCRYPTION_KEY` and `CLERK_SIGN_IN_URL` secret. All OAuth artifacts live in Workers KV.

5

What transport does the server use?

It uses Streamable HTTP (MCP spec 2025‑03‑26). For older clients that don’t support this transport, a stdio bridge is available via the npm package `@quelvio/mcp-server`.

评论

记忆与知识 分类下的更多 MCP 服务器

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Orcha

westonhancock

Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age

Semantic Ui React

Semantic-Org

The official Semantic-UI-React integration

13.2K

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

广告合作