vexo
Vexo's official Claude Code plugin marketplace.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/vexotech--vexo-mcp-plugin)HTML
<a href="/listings/vexotech--vexo-mcp-plugin"><img src="/api/listings/vexotech--vexo-mcp-plugin/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Add this marketplace, then install the plugin:
/plugin marketplace add vexotech/vexo-mcp-plugin /plugin install vexo@vexo
The plugin registers the `vexo` MCP server. To sign in:
1. Run `/mcp`. 2. Select **vexo**, and choose **Authenticate**. A browser window opens. 3. Sign in to Vexo, and on **Authorize access**, click **Approve**.
Then ask questions in plain language, or run `/vexo:connect` to see your apps and example prompts.
The plugin's connection is read-only. To let Claude Code change data, see [Allow changes](#allow-changes).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 21 lines
- {
- "name": "vexo",
- "description": "Vexo's official Claude Code plugin marketplace.",
- "version": "0.2.0",
- "owner": {
- "name": "Vexo",
- "email": "support@vexo.co",
- "url": "https://www.vexo.co"
- },
- "plugins": [
- {
- "name": "vexo",
- "source": "./plugins/vexo",
- "description": "Query your Vexo analytics, session replays, and errors from Claude Code via MCP, and triage errors with write access.",
- "version": "0.2.0",
- "author": { "name": "Vexo", "url": "https://www.vexo.co" },
- "homepage": "https://www.vexo.co",
- "keywords": ["analytics", "react-native", "mcp", "session-replay", "vexo"]
- }
- ]
- }
README.md · README · 110 lines
- # Vexo MCP
- Ask your AI coding tools about your [Vexo](https://www.vexo.co) analytics, session replays, and errors. The Vexo MCP
- server is at `https://api.vexo.co/mcp` and speaks the Model Context Protocol over HTTP (protocol version
- `2025-06-18`). Every tool works only on the apps your account can access: the apps you own and the apps a team shares
- with you.
- ## Tools
- Read tools work with every connection:
- | Tool | What it does |
- | --- | --- |
- | `list_apps` | Lists the apps you can access, with the id every other tool takes as `app_id`. |
- | `query_events` | Answers a plain-language analytics question about one app, for example "top 10 screens by errors last week". Returns rows and the SQL it ran. |
- | `get_stats` | Returns an app's total events, distinct users, and distinct sessions in a time window. |
- | `list_replays` | Lists session replays, newest or longest first, with filters for errors, rage taps, user, screen, app version, and OS. |
- | `get_session_timeline` | Reads one session's events in time order: screens, taps, custom events, network requests, logs, and errors. |
- | `list_error_groups` | Lists deduplicated errors with counts, app versions, triage status, and assignee. |
- | `get_error_group` | Returns one error's newest occurrence with its stack trace, and the sessions that hit it with their replays. |
- | `list_dashboards` | Lists dashboards and the saved insights (trends and funnels) on each. |
- | `get_insight` | Runs a saved insight over a time window and returns the numbers the dashboard shows. |
- | `get_funnel` | Returns a saved funnel's conversion per step, optionally broken down by OS, app version, country, or an event property. |
- | `list_cohorts` | Lists saved cohorts and their definitions. |
- | `count_cohort` | Counts the users in a saved cohort over a time window. |
- | `list_heatmap_screens` | Lists heatmap screens with their tap counts. |
- Write tools need the `mcp:write` scope (see [Allow changes](#allow-changes)):
- | Tool | What it does |
- | --- | --- |
- | `set_error_group_status` | Sets an error group to `OPEN`, `RESOLVED`, or `IGNORED`. Needs write access to the app. |
- | `add_session_comment` | Adds a comment to a session, optionally pinned to a playback position. |
- Tools that read events take a time window as `from` and `to` in milliseconds since the Unix epoch. It defaults to the
- last 28 days and can span at most 366 days. For every parameter, see the
- [MCP tool reference](https://docs.vexo.co/settings/mcp-server#tool-reference).
- ## Install in Claude Code
- Add this marketplace, then install the plugin:
- ```
- /plugin marketplace add vexotech/vexo-mcp-plugin
- /plugin install vexo@vexo
- ```
- The plugin registers the `vexo` MCP server. To sign in:
- 1. Run `/mcp`.
- 2. Select **vexo**, and choose **Authenticate**. A browser window opens.
- 3. Sign in to Vexo, and on **Authorize access**, click **Approve**.
- Then ask questions in plain language, or run `/vexo:connect` to see your apps and example prompts.
- The plugin's connection is read-only. To let Claude Code change data, see [Allow changes](#allow-changes).
- ## Allow changes
- The write tools need an OAuth token with the `mcp:write` scope. Claude Code asks for the scopes in a server's
- `oauth.scopes` setting, so add a second, write-enabled server for your user:
- ```
- claude mcp add-json --scope user vexo-write '{"type":"http","url":"https://api.vexo.co/mcp","oauth":{"scopes":"mcp mcp:write"}}'
- ```
- Then run `/mcp`, select **vexo-write**, and choose **Authenticate**. The **Authorize access** screen says that the
- connection can make changes. Without the scope, a write tool returns an error that names `mcp:write`.
- ## Install in Claude Desktop or Cursor
- These clients connect with a static config entry. Create a
- [personal access token](https://docs.vexo.co/settings/api-tokens) in the Vexo dashboard, then add the server to your
- MCP config (`claude_desktop_config.json` for Claude Desktop, or your Cursor MCP settings), and replace
- `YOUR_VEXO_TOKEN` with your token:
- ```json
- {
- "mcpServers": {
- "vexo": {
- "type": "http",
- "url": "https://api.vexo.co/mcp",
- "headers": {
- "Authorization": "Bearer YOUR_VEXO_TOKEN"
- }
- }
- }
- }
- ```
- A personal access token is read-only: it can call every read tool but no write tool.
- ## MCP Registry
- [`server.json`](./server.json) lists the Vexo MCP server in the
- [Official MCP Registry](https://registry.modelcontextprotocol.io) as `io.github.vexotech/vexo-analytics`, a remote
- server at `https://api.vexo.co/mcp` over Streamable HTTP. MCP clients that read the registry connect to it and sign in
- with OAuth, the same as the Claude Code plugin.
- To change the listing, edit `server.json`, set a new `version` (the registry never changes a published version), and
- publish it with [`mcp-publisher`](https://github.com/modelcontextprotocol/registry/blob/main/docs/modelcontextprotocol-io/quickstart.mdx).
- ## Support
- - Docs: [MCP server](https://docs.vexo.co/settings/mcp-server)
- - Website: https://www.vexo.co
- ## License
- MIT. See [LICENSE](./LICENSE).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.