Skip to main content
Ask your SourceMedium data questions from the AI you already use. Every agent uses one URL and your SourceMedium sign-in. It reads your data and never changes it, and you never paste BigQuery, Shopify, or Meta credentials. Newer connections can also send SourceMedium a rating of an answer, with a reason and an optional short comment (submit_feedback). Want SourceMedium to write the SQL for you? Use SourceMedium Agent in Slack. Prefer to watch first? The Connect an agent walkthrough is a short narrated demo of the same steps.
Any workspace member can connect. Sign in with your membership email. The session cannot change your data and sees only what you already can.

The connection URL

Keep the /mcp. The AI Agents page in your workspace has it ready to copy and confirms when your agent connects. Another MCP client may work with the same URL. These are the ones we keep steps for.
When you connect SourceMedium to an AI service, queries and the resulting data may be sent to the AI provider you choose. Access remains limited by your existing SourceMedium organization membership and connected-source permissions. This connection does not provide semantic PII detection or field-level masking. Do not request customer contact, address, or other direct personal data unless it is necessary and authorized for your use case.

Chat apps

On Team, an Owner or Primary Owner adds SourceMedium under Organization settings → Connectors → Add → Custom → Web. On Enterprise, a custom role with Manage access to Libraries can also add it. Members then connect it under Customize → Connectors.
1

Open connectors

Open Claude connector setup. On Team or Enterprise, use Customize → Connectors to find the connector your organization added instead.
2

Add the connector

On Free, Pro, Max, or Ultra, use the Add custom connector form. On Team or Enterprise, click Connect on the connector your organization added and skip the next step.
3

Paste the URL

Enter SourceMedium as the name and https://mcp.sourcemedium.com/mcp as the MCP server URL. Click Continue, review the detected authentication settings, and finish adding the connector.
4

Sign in

Sign in with your SourceMedium account and approve.
5

Ask

In a chat, click +, open Connectors, switch SourceMedium on, and ask.
Claude’s Free plan allows one custom connector.
On paid plans Claude Data can read SourceMedium through this connection. Each viewer needs their own SourceMedium connection to refresh live charts. Check Claude’s sharing options for your plan and workspace. On Team or Enterprise, an Owner may first need to turn on Claude Data (Organization settings → Artifacts) and artifact connectors (Organization settings → Capabilities).
Vendor guide: Claude custom connectors

Agents

1

Add it

2

Sign in

Run claude mcp login sourcemedium and complete the browser sign-in. You can also use /mcp inside Claude Code.
3

Ask

Ask a question about your data.
To sign out, run claude mcp logout sourcemedium before removing the server.
Vendor guide: Claude Code MCP
Want your coding agent working in your warehouse directly? Add SourceMedium Agent Skills too. They keep this connection and build dashboards and pipelines with your own gcloud login.

When your agent opens SourceMedium

Every agent above sends you to the same SourceMedium sign-in at its sign-in step:
  1. Continue with Google, or enter the email you use for SourceMedium. Use the same account you use in your workspace.
  2. Click Allow access. One connection reaches one organization. If you belong to more than one, pick it under Organization access. To use a different organization later, open a private window and connect again.
A sign-in step on the AI Agents page, showing the SourceMedium sign-in screen and the Organization access screen with Allow access A sign-in step on the AI Agents page, showing the SourceMedium sign-in screen and the Organization access screen with Allow access

If connecting fails

  • Sign-in failed? Try signing in again or reconnecting in your assistant. Before removing a personal or shared connection, follow Agent connection troubleshooting.
  • Claude Code? Run claude mcp login sourcemedium. To reset saved credentials, run claude mcp logout sourcemedium, then claude mcp login sourcemedium.
  • 401, ACCESS_DENIED, or the wrong organization? See Agent connection troubleshooting.

After you connect

One connection is one organization. In several workspaces? Pick one at sign-in. To switch, open a private window, connect again, and pick the other organization. The browser may retain the previous sign-in, even after you sign out of the assistant’s connection. In Claude Code, run claude mcp logout sourcemedium, then claude mcp login sourcemedium to authorize again. The AI Agents page lists every agent you’ve connected, and when it was last used: Your own agent on the AI Agents page, listing Claude and Claude Code with when each connected and was last used Your own agent on the AI Agents page, listing Claude and Claude Code with when each connected and was last used

What it can reach

Not connected? That tool answers SOURCE_UNAVAILABLE, and warehouse questions still work. Agency partners with a live grant can connect too. A brand- or store-scoped grant sees only those stores and can’t run raw SQL.

Google Sheets tables

A Google Sheet connected to your BigQuery project as a table works like any other table, once SourceMedium can open the sheet. A sheet starts out unshared. SourceMedium opens sheets as one address for your organization and checks each one for you.
  1. Open Data catalog → AI instructions in SourceMedium. The Google Sheets section lists every Sheets table in your warehouse as Ready, Needs sharing, or Couldn’t check. Copy the address shown there.
  2. For each table that needs sharing, click Open sheet, then Share.
  3. Paste the address, choose Viewer, untick Notify people, and click Share.
  4. Back on AI instructions, click Check again. The table shows Ready.
Just added a Sheets table? Click Check again to see it right away. SourceMedium also rechecks every sheet about every 15 minutes, and get_data_context tells your agent which tables it can’t read yet. Only someone who can share the sheet can do this. Not yours? Ask its owner. A sheet in a SourceMedium shared drive is shared by your SourceMedium team. If your Google Workspace blocks sharing outside your company, your admin has to allow the address first. If your agent queries a sheet before it is shared, it gets PROVIDER_PERMISSION_DENIED. The error links the sheet and gives the address, so the agent can tell you exactly what to share.

Your own tables

Your own tables are reachable in a dedicated project when you are a direct member of it. The agent queries only the datasets get_data_context lists. A dedicated project comes with Pro. On Foundation your data lives in a shared BI project, so the agent reaches SourceMedium’s tables and the raw tables you select, not tables of your own (Foundation and Pro). Selected raw tables land in your workspace’s own dataset on the shared project, and agents read them through SourceMedium MCP. On Pro they land in your BigQuery project. The MCP tool reference explains how the catalog reports a table it can see but has no definition for. Your own tables have no SourceMedium definition, so the agent cannot find them by what they mean. Name the table in the question:
According to ops.store_sales, how many units did we sell in September 2026, by store?
Give the dataset and table, without the project. Every query runs in the project get_data_context names for your organization, so ops.store_sales is enough. A question that only describes the table (“our stock table”) sends the agent to the catalog, and it may land on a SourceMedium table that covers similar ground. If you do not know the exact name, ask for it by part of the name first (“find the table with inventory in its name”). Example prompts. Each names the table, states the window, asks for the figure, and adds the one caveat its table needs:
Expect the agent to call get_data_context first. It then calls search_data_catalog with the table name, which reports the table as live and uncatalogued. Next it reads the columns: search_data_catalog with the table as dataset.table, or on the earlier tool set INFORMATION_SCHEMA.COLUMNS through run_bigquery_sql. Then the query runs. If the answer does not include a check (rows against distinct keys, nulls, a second method that should agree), ask for one. The numbers carry no SourceMedium validity filter. When you reconcile one of your tables with a SourceMedium table, ask for the match by store, day and SKU. Expect two differences. First, SourceMedium’s figures apply is_order_sm_valid, so draft, cancelled and refunded orders drop out, and your table may not. Second, SKU case can differ between the two. Four things can trip a question up, and all four come from how the data was loaded:
  • Fixed-width status values. Some system exports pad status values to a fixed width, so an exact match on Open can return nothing. If a status count comes back as zero, ask the agent to trim the values first.
  • Sync copies. A table replicated from a database can keep every sync, so a count of rows is a count of copies. Say “this table keeps a copy of every sync” in the question, and ask for the latest copy of each record with soft-deleted rows left out. If the answer does not mention duplicates, ask whether it checked.
  • Daily snapshots. A snapshot table holds one row per item per day, so a sum over it means nothing. Ask for “the most recent date in the table” and the figures on that date, as the inventory prompt above does.
  • UTC freshness. Load and rebuild times come from the warehouse clock, marked “UTC”. Ask for times in your store’s timezone if that is what you compare against.
Set these rules once in a Claude or ChatGPT project and every chat inherits them. See Set up a project for your data.

Your first question

Paste this in:
Compare net revenue for the last complete week against the week before, using SourceMedium’s own metric definition (query_metrics). Tell me which stores, dates, and timezone you used, and show the definition and any filters.
A good answer names your stores, the right dates, and the definition it used. Checking it against a dashboard? Match dates, timezone, stores, and filters first. The MCP tool reference explains every tool.

Limits

MCP tool reference

Every tool, and the order that gets correct answers.

Agent connection troubleshooting

Sign-in errors, source denials, and what to send support.

Set up a project for your data

Name your tables once in a Claude or ChatGPT project, with instructions to paste.

SourceMedium Agent

Ask in Slack and let SourceMedium write the SQL and charts.