Mcp Server

quelvio/quelvio-mcp-server

Quelvio turns your company's Google Drive, SharePoint, Confluence, Slack, and Notion into a queryable knowledge base for AI agents. It exposes three tools: query_knowledge (with fast, standard, and deep modes), list_domains for discovery, and get_source_detail for citation provenance. Every query respects individual source permissions, so you only see what your actual account can access in those systems. No API keys to manage. First use triggers an OAuth flow through your company's Clerk-hosted sign-in, then your client reuses the token. Queries cost knowledge tokens (1,500 to 25,000 depending on mode), while discovery and provenance tools are free. Use it when you need cited answers from internal docs without switching contexts or worrying about cross-employee data leakage.

tools: 3
transport: HTTP
last updated: May 18, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://mcp.quelvio.com/http --name quelvio

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http quelvio https://mcp.quelvio.com/http

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 3 tools

Verified live against the running server on Nov 6, 2026.

query_knowledgeSearch 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: `fa...4 params

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: `fa...

Parameters* required

domainstring

Optional taxonomy domain filter (e.g. 'engineering.platform'). Use `list_domains` to discover valid values for the tenant.

max_sourcesnumber

Number of source chunks to return (1–20, default 5). The 25K token cap may force fewer results regardless of this value.

modestring

fast | standard | deep. Defaults to `standard`. `fast` returns chunks only (no synthesized answer); `standard` and `deep` return a synthesized answer with [n] citations + the source chunks.one of fast · standard · deep

query*string

Natural-language query (1–2000 characters). Be specific — results are ranked by authority + relevance, not keyword overlap.

list_domainsList 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...1 params

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...

Parameters* required

coverage_filterstring

Optional comma-separated subset of expert,partial,none. Default: all three. Unknown tokens 400.

get_source_detailReturn 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_knowled...1 params

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_knowled...

Parameters* required

query_id*string

UUID returned in the structured-metadata block of a prior `query_knowledge` response. Tenant-scoped — cross-tenant 404.

Readme

@quelvio/mcp-server

Quelvio MCP server — search your company's connected knowledge from any AI tool that speaks the Model Context Protocol.

Endpoint: https://mcp.quelvio.com/http (Streamable HTTP, MCP spec 2025-03-26) Source: Quelvio/quelvio-mcp-server License: MIT

Tools

Tool	Purpose	Knowledge Tokens
`query_knowledge`	Primary search across the tenant's connected sources (Drive, SharePoint, Confluence, Slack, Notion). Modes: `fast`, `standard` (default), `deep`.	1,500 kT (`fast`) / 12,500 kT (`standard`) / 25,000 kT (`deep`)
`list_domains`	Discovery — list taxonomy domains with coverage levels. Use to decide whether the brain has relevant knowledge before issuing a billable query.	0 kT
`get_source_detail`	Per-chunk provenance for a previous query: document path, lifecycle state, embedding timestamp, contributor, last-updated. Pass a `query_id` from an earlier `query_knowledge` response.	0 kT

Permission model

Every MCP query is scoped to your individual employee identity, not just your tenant. The server applies the same three-layer access model the dashboard uses:

View the full README on GitHub

Details

Repository: github.com/quelvio/quelvio-mcp-server
Website: quelvio.com
Categories: Sales & Marketing, Documents & Knowledge
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related Sales & Marketing MCP servers

View all

Google Maps Mcp Servercom.thenextgennexus/google-maps-mcp-serverOpenStreetMap local-business search, lead generation and email validation as agent tools.0stars

VarynForgecom.varynforge/serverSEO research SaaS exposed as 30+ MCP tools. Forge niche analysis, plans, and writer-ready briefs.0stars

NDI-MCP-Servercreintel/ndi-mcp-serverCommercial real estate deal search, comp lookup, and scoring for the Northeast US0stars

Meok Omnibus Tracker Mcpcsoai-org/meok-omnibus-tracker-mcpEU Digital Omnibus AI Act tracker - Track delay status by article. First-mover advantage for SEO + b0stars

AccuRanker MCP Server and API by Cotletcotlet-connect/accuranker-mcpAccuRanker SEO rank tracking MCP server: add keywords, list keywords and ranks.0stars

Idealista MCP Server and API by Cotletcotlet-connect/idealista-mcpIdealista property sales and rentals MCP server: list my listings, update listing, renew listing.0stars