Who it is for
Analytics teams that publish in Evidence and want their existing reports and tables queried from a conversation.
Overview
Evidence is a business intelligence tool where reports are written in SQL and Markdown and then published. This connector links a chat session to an Evidence account and the live data behind it.
Four things become possible once connected: browsing metadata about available tables, running queries that read but never modify data, searching published reports by term, topic or metric, and pulling the AI context an organization has stored in Evidence so answers follow in house reporting conventions. A report page can be returned as its written content or as a structured breakdown of the queries and components it contains.
Access follows the permissions already attached to the connected account, and the query path is read only.
Analytics teams that publish in Evidence and want their existing reports and tables queried from a conversation.
Stored reporting context is retrievable, so answers can follow the definitions an organization already uses in its published work.
Availability
Evidence Technologies ships this on both marketplaces: Evidence Studio is listed in the Claude connectors directory and in the ChatGPT apps directory, under the same publisher domain.
Only 392 of the 3,150 products in this directory are listed in both marketplaces. One MCP server can serve both surfaces; what differs is each platform's listing and review process.
ChatGPT listing
Claude listing
Evidence Studio publishes 11 tools to Claude. That is a mid-sized surface: 48% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Data & Analytics publishes 12, so this one sits one tool below its bucket's median, 104th of 198.
It falls in the 11-20 tools band, which holds 22.5% of the Claude directory.
Evidence Studio publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://evidence.studio/api/mcp Evidence Studio is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
Evidence is an AI-powered BI tool for publishing reports using SQL and Markdown. This connector lets Claude work with your organization's live data and published reports on your behalf - securely, and scoped to your own permissions. After you connect your Evidence account, Claude can: - Browse table metadata - Run read-only queries against data stored in Evidence - Search your published reports by topic, metric, or term, and read a page's content or a structured summary of its queries and components - Retrieve AI context stored in Evidence - so answers match how your organization reports Requires an Evidence account with workspace access. Learn more at https://evidence.dev
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Web analytics questions answered with session-level evidence
Claude
Query security operations data: alerts, investigations and audit logs
Claude
Site traffic and ad revenue metrics for publishers
Claude · ChatGPT
Thai accounting data: sales, expenses, invoices and full financials
Claude
Social and paid social performance analysis over a content library
Claude
Query Adobe Customer Journey Analytics metrics, dimensions, and segments
Claude
This is an independent catalogue entry compiled by Node8 from Evidence Studio's public marketplace listings as they stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Evidence Technologies, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.