Model Context Protocol server for Vynix. It gives coding agents direct access to visual feedback, bug reports, screenshots, diagnostics, comments, and issue workflows so agents can reason from real context instead of guessing.
- Feedback with evidence: page metadata, target element, screenshot, console/network context.
- End-to-end execution: inspect feedback, diagnose, generate coding prompts, create GitHub issues, update status, comment.
- Agent-safe hints: read-only/idempotent/open-world annotations for better approval behavior in MCP clients.
- Registry-ready metadata for modern MCP directories.
- Product screenshot placeholder: docs/assets/screenshot-dashboard.png
- Annotation workflow GIF placeholder: docs/assets/workflow-fix-annotation.gif
flowchart LR
A[MCP Client\nClaude/Cursor/Copilot/VS Code] -->|stdio or streamable-http| B[Vynix MCP Server]
B --> C[Vynix API]
B --> D[GitHub API via Vynix backend]
C --> E[Projects]
C --> F[Annotations]
C --> G[Screenshots and diagnostics]
- 17 production tools for read and write workflows.
- Resource catalog for server metadata, tool/prompt/skill references, and contextual summaries.
- Workflow prompts for QA, release readiness, PM briefings, and engineering planning.
- Dual transport support:
stdioand Streamable HTTP. - Auth via API token or email/password refresh flow.
Node.js 18+ is required.
{
"mcpServers": {
"vynix": {
"command": "npx",
"args": ["-y", "@usevynix/mcp-server"],
"env": {
"VYNIX_API_URL": "https://www.vynix.in",
"VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
}
}
}
}npm install -g @usevynix/mcp-server
vynix-mcpdocker run --rm -i \
-e VYNIX_API_URL=https://www.vynix.in \
-e VYNIX_API_TOKEN=PASTE_YOUR_TOKEN_HERE \
ghcr.io/usevynix/vynix-mcp:latestgit clone https://github.com/UseVynix/vynix-mcp.git
cd vynix-mcp
npm install
npm run build
npm run check
node dist/index.jsUse claude_desktop_config.json:
{
"mcpServers": {
"vynix": {
"command": "npx",
"args": ["-y", "@usevynix/mcp-server"],
"env": {
"VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
}
}
}
}Diagnostics are written to stderr; stdout is reserved for the protocol stream.
Use ~/.cursor/mcp.json.
{
"mcpServers": {
"vynix": {
"command": "npx",
"args": ["-y", "@usevynix/mcp-server"],
"env": {
"VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
}
}
}
}Use .vscode/mcp.json with top-level servers:
{
"servers": {
"vynix": {
"command": "npx",
"args": ["-y", "@usevynix/mcp-server"],
"env": {
"VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
}
}
}
}Use your Windsurf MCP config file with this server block:
{
"mcpServers": {
"vynix": {
"command": "npx",
"args": ["-y", "@usevynix/mcp-server"],
"env": {
"VYNIX_API_TOKEN": "PASTE_YOUR_TOKEN_HERE"
}
}
}
}For hosted mode, use the Streamable HTTP endpoint:
- Base URL:
https://mcp.vynix.in/mcp - OAuth discovery:
/.well-known/oauth-authorization-server
See examples/configs/mcp.json.
Environment variables:
VYNIX_API_URL(optional, default:https://www.vynix.in)VYNIX_API_TOKEN(recommended)VYNIX_API_EMAILandVYNIX_API_PASSWORD(fallback login mode)VYNIX_MCP_MODE(stdioorhttp)VYNIX_MCP_HOST,VYNIX_MCP_PORT,VYNIX_MCP_PATH(HTTP mode)
Generate a token from: https://www.vynix.in/mcp
- Tool reference: docs/tools.md
- Prompt reference: docs/prompts.md
- Resource reference: docs/resources.md
- Skill/workflow reference: docs/skills.md
- Deployment guide: docs/deployment.md
- Agent discovery guide: docs/agent-discovery.md
- LLM index file: llms.txt
- Directory listing tracker: docs/listings-status.md
- Conversation workflows: examples/workflows
- Prompt library (100+ prompts): examples/prompts.md
Not configurederror: setVYNIX_API_TOKENor bothVYNIX_API_EMAILandVYNIX_API_PASSWORD.401errors: regenerate token and verify API URL.- No tools listed: confirm the MCP config key (
mcpServersvsservers) for your client. - Hosted mode not reachable: verify
VYNIX_MCP_MODE=httpand check/health.
Only diagnose_annotation can invoke external AI providers through your Vynix workspace configuration.
No. It includes read tools and write tools. MCP annotations identify mutating/open-world calls so clients can request confirmation.
Yes. Run in stdio mode locally or HTTP mode behind your own infrastructure.
See CONTRIBUTING.md. For local validation run:
npm run check- Never commit API tokens.
- Prefer short-lived tokens where possible.
- See SECURITY.md (create one if your org requires a disclosure policy).