ENDPOINT 1
https://mcp.vynix.in/mcp
MCP server metadata
- Name
- vynix
- Version
- 0.1.2
Vynix is the source of truth for website feedback and annotations. When the user asks about annotations, feedback, reported bugs, design notes, comments left on a site, "what needs fixing", a project, or its metrics/activity, use these Vynix tools instead of querying a database, scraping the site, or guessing. Typical flow: 1. Call list_projects to find the project (match by name or website_url, e.g. the user gives a domain like demo.example.com). 2. Call list_annotations with that project_id. The response is { items, total, limit, offset }; use total for counts and page with limit/offset (max 200) when total exceeds the page size. Filter with status / type / priority. 3. Drill into one item with get_annotation, get_annotation_screenshots, and get_annotation_analysis for full captured context and any AI diagnosis. 4. To work an item: update_annotation_status, add_comment, generate_prompt, or diagnose_annotation. Use get_metrics / get_activity for project-wide overviews. Never fabricate annotation data. If no token or project is configured, say so.
Known tools 17
list_annotationsList a project’s annotations, optionally filtered by status, type, or priority.
Inferred read-onlyget_annotationFetch one annotation with its full captured context: page, target element (selector, XPath, styles), surrounding DOM, and runtime diagnostics (console + network).
Inferred read-onlyget_annotation_analysisRead the latest stored AI diagnosis for an annotation (root causes, confidence, suggested fix, and likely source files).
Inferred read-onlyget_annotation_screenshotsReturn the region screenshots attached to an annotation as viewable images, so you can see exactly what the reporter pointed at.
Inferred read-onlylist_annotation_issuesList the tracker (GitHub) issues opened from an annotation, with each issue’s live state.
Inferred read-onlylist_project_issuesList every tracker issue across a project, with an open/closed/agent summary.
Inferred read-onlygenerate_promptRender a ready-to-paste coding prompt for an annotation, formatted for a target assistant.
Inferred read-onlyget_metricsOverview of your projects: KPI counts, status breakdown, a daily time series, and recent activity.
Inferred read-onlyget_activityRecent activity feed for a project (status changes, comments, issues, members).
Inferred read-onlydiagnose_annotationRun the AI Diagnosis Engine on an annotation: it analyses the captured page, element, DOM, and runtime errors to produce ranked root causes, a confidence score, a suggested fix, and the likely source files.
Inferred read-onlycreate_share_linkMint a read-only public review link for a project, so a stakeholder can review its annotations without an account.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.vynix]
url = "https://mcp.vynix.in/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"vynix": {
"type": "http",
"url": "https://mcp.vynix.in/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: vynix
Remote MCP URL: https://mcp.vynix.in/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"vynix": {
"url": "https://mcp.vynix.in/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"vynix": {
"type": "http",
"url": "https://mcp.vynix.in/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "vynix",
"transport": "streamable-http",
"url": "https://mcp.vynix.in/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.