# Databuddy MCP server

> Query traffic, funnels, session replays and errors, and manage goals, feature flags and short links in Databuddy analytics.

- Listing: https://mcp.tc/i/databuddy
- Connect: use the server's own URL `https://api.databuddy.cc/v1/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [Data & Analytics](https://mcp.tc/c/analytics)
- Vendor: Databuddy
- Homepage: <https://www.databuddy.cc/mcp>
- Docs: <https://www.databuddy.cc/docs/api/mcp>
- Repository: <https://github.com/databuddy-analytics/Databuddy>

## About

Connects an AI agent to Databuddy product analytics. It can read traffic, referrers, devices, errors, Web Vitals, funnels, goals and session replays, and it can set up goals, funnels, feature flags and short links. About 33 tools are offered.

Changes to your data show a preview first and wait for your confirmation. The server runs as a hosted streamable HTTP endpoint at https://api.databuddy.cc/v1/mcp. Users sign in with Databuddy in the browser the first time the client connects.

## What it can do

- Query traffic, pages, referrers, devices, errors and Web Vitals
- Search session replays by page, click or event
- Analyze funnel conversion and drop-off
- Create and update goals and funnels after confirmation
- Manage feature flags, rollouts and variants
- Read published insights and investigations

## Tools (46)

- `list_websites`: List the websites this account can access, with IDs, names, domains, and organizations. (read-only)
- `capabilities`: List the get\_data query types by category, with date presets and a schema summary. (read-only)
- `get_schema`: Return the analytics tables execute\_sql\_query can read, with column types and the counting rules for each table. (read-only)
- `get_data`: Query website analytics: traffic, pages, referrers and UTM campaigns, devices, countries, errors, Web Vitals, sessions, users, custom events, revenue, uptime and AI traffic. (read-only)
- `execute_sql_query`: Run read-only ClickHouse SQL over one website's published analytics tables. (read-only)
- `get_business_context`: Return the organization's saved business context: what it does, what its events mean, team priorities, success definitions and measurement plans. (read-only)
- `check_tracking`: Check whether a website's tracking is installed and receiving page views, with blocked-request issues, their fix, and the latest coding-agent install report. (read-only)
- `list_profile_traits`: List identified-user trait keys such as plan or role, with how many profiles have each and their top values. (read-only)
- `search_replays`: Find recordings by email, profileId, current user traits, recording dates, pages, timeline text, events, activity, or watch score. (read-only)
- `list_replay_issues`: List the last week's session replay friction: page elements whose clicks got no response (dead, rage or unresponsive clicks), most widespread first. (read-only)
- `list_accounts`: Find customer accounts (groups such as workspaces or companies) with plan, billing status, MRR and activity for a period. (read-only)
- `get_account`: Return one customer account: its traits and billing, activity for a period, the identified users active in it, its health and the account reviewer's last review. (read-only)
- `list_changes`: List metric changes Databuddy detected in the last two days for an organization or website, critical and largest first. (read-only)
- `list_insights`: List published insights for an organization or website: title, summary, evidence, impact, and the recorded next step (null when no step was recorded, when a later finding for the same case superseded it, or when the… (read-only)
- `list_investigations`: List the latest investigation per subject with IDs. (read-only)
- `get_investigation`: Get one durable investigation, including its current status, evidence-backed observations, and replies. (read-only)
- `reply_to_investigation`: Add a clarification to an existing investigation.
- `dismiss_investigation`: Close an open investigation with the team's reason, only when the user asks. (can modify or delete data)
- `list_funnels`: List funnels for a website with their steps and filters. (read-only)
- `get_funnel_analytics`: Return per-step conversion and drop-off for one funnel, by funnelId from list\_funnels. (read-only)
- `get_funnel_analytics_by_referrer`: Return one funnel's conversion broken down by referrer, by funnelId from list\_funnels. (read-only)
- `create_funnel`: Create a funnel for a website.
- `update_funnel`: Change a saved funnel's name, steps, filters, or conversion window for future analytics reads. (can modify or delete data)
- `delete_funnel`: Delete a saved funnel. (can modify or delete data)
- `list_goals`: List conversion goals for a website with their type, target, and filters. (read-only)
- `get_goal_analytics`: Return entered and completed counts and the conversion rate for one goal, by goalId from list\_goals. (read-only)
- `create_goal`: Create a conversion goal.
- `update_goal`: Change a saved conversion goal used by future analytics reads. (can modify or delete data)
- `delete_goal`: Delete a saved conversion goal. (can modify or delete data)
- `list_annotations`: List chart annotations for a website: text, time range, tags, color, and visibility. (read-only)
- `create_annotation`: Create a chart annotation.
- `update_annotation`: Update an annotation's text, tags, color, or visibility. (can modify or delete data)
- `delete_annotation`: Delete a chart annotation from dashboard charts, including public charts if shared. (can modify or delete data)
- `list_links`: List short links for the website's organization, newest first, with every folder and its link count. (read-only)
- `search_links`: Find short links across the full catalog matching a substring on name, slug, target URL, or external ID, newest first. (read-only)
- `get_link_analytics`: Return click analytics for one short link by ID from list\_links or search\_links: total clicks, clicks by day, and top referrers, countries and devices for a date range. (read-only)
- `create_link`: Create a short link in the website's organization.
- `update_link`: Change a saved short link, affecting subsequent redirects and social previews. (can modify or delete data)
- `delete_link`: Delete a short link. (can modify or delete data)
- `list_flags`: List feature flags with their status, rollout, rules, and variants: a website's flags when a website is given, otherwise the organization-wide flags. (read-only)
- `get_experiment_results`: Return exposed/converted visitors and statistical comparisons per flag arm. (read-only)
- `create_flag`: Create a feature flag, inactive and boolean unless configured.
- `update_flag`: Change live flag evaluation settings. (can modify or delete data)
- `add_users_to_flag`: Change who receives a flag by targeting site user IDs or emails. (can modify or delete data)
- `delete_flag`: Archive a feature flag so SDKs stop serving it. (can modify or delete data)
- `submit_feedback`: Send a bug report, feature request, or blocking error about Databuddy itself to the Databuddy team.

## Example prompts

- "Why did signups drop last week? Check the funnel and replays."
- "Which pages do ChatGPT visitors land on?"
- "List my feature flags and their rollout status."
- "Create a conversion goal for the pricing page."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http databuddy https://api.databuddy.cc/v1/mcp
```

2. Start Claude Code, type `/mcp`, pick **databuddy** and choose **Authenticate**. A browser window opens for the Databuddy sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Databuddy** and paste this URL:

```url
https://api.databuddy.cc/v1/mcp
```

3. Click **Add**, then **Connect**, and sign in when Databuddy asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Databuddy&connectorUrl=https%3A%2F%2Fapi.databuddy.cc%2Fv1%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://api.databuddy.cc/v1/mcp` and click **Add**.

3. Click **Connect** and sign in when Databuddy asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://api.databuddy.cc/v1/mcp` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Databuddy to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=databuddy&config=eyJ1cmwiOiJodHRwczovL2FwaS5kYXRhYnVkZHkuY2MvdjEvbWNwIn0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "databuddy": {
      "url": "https://api.databuddy.cc/v1/mcp"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=databuddy&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fapi.databuddy.cc%2Fv1%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"databuddy","type":"http","url":"https://api.databuddy.cc/v1/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "databuddy": {
      "type": "http",
      "url": "https://api.databuddy.cc/v1/mcp"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "databuddy": {
      "serverUrl": "https://api.databuddy.cc/v1/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add databuddy --url https://api.databuddy.cc/v1/mcp
codex mcp login databuddy
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.databuddy]
url = "https://api.databuddy.cc/v1/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http databuddy https://api.databuddy.cc/v1/mcp
```

Then, inside Gemini CLI, run `/mcp auth databuddy` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "databuddy": {
      "type": "http",
      "url": "https://api.databuddy.cc/v1/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://api.databuddy.cc/v1/mcp`.

## Recent changes

- 2026-11-14 20:51 UTC: 9 tools changed. Source: automatic check. Changed: create\_funnel, create\_goal, dismiss\_investigation, get\_data, get\_funnel\_analytics, get\_goal\_analytics, list\_accounts, update\_funnel, update\_goal.
- 2026-11-14 14:51 UTC: 12 tools added, 1 tool removed and 34 tools changed. Server instructions changed. Source: automatic check. Worth a look: a tool lost its read-only hint or gained a destructive one, a new tool is marked destructive and new server instructions. Added: check\_tracking, delete\_flag, delete\_funnel, execute\_sql\_query, get\_account, get\_business\_context, get\_link\_analytics, list\_accounts, list\_changes, list\_profile\_traits, list\_replay\_issues, update\_funnel. Removed: list\_link\_folders. Changed: add\_users\_to\_flag, capabilities, create\_annotation, create\_flag, create\_funnel, create\_goal, create\_link, delete\_annotation, delete\_goal, delete\_link, dismiss\_investigation, get\_data, get\_experiment\_results, get\_funnel\_analytics, get\_funnel\_analytics\_by\_referrer, get\_goal\_analytics, get\_investigation, get\_schema, list\_annotations, list\_flags and 14 more.
- 2026-11-10 00:04 UTC: Tracking started: 35 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/databuddy#history (Atom feed: https://mcp.tc/i/databuddy/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2026-07-28
- Last checked: 2026-11-18 (reachable)
- Listed: 2026-10-29
- Updated: 2026-11-14

---
Source: https://mcp.tc/i/databuddy (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
