VIBE ANNOTATIONS SERVER TOOLS

6 tools from the Vibe Annotations Server MCP Server, categorised by risk level.

View the Vibe Annotations Server policy →

// ALL 6 VIBE ANNOTATIONS SERVER TOOLS

READ 4 tools

Read get_annotation_screenshot Retrieves screenshot data for a specific annotation when visual context is needed to understand and impleme... Read get_project_context Analyzes a localhost development URL to infer project framework and technology stack context. This tool hel... Read read_annotations Retrieves user-created visual annotations with pagination support. Returns annotation data with has_screens... Read watch_annotations Watch for new annotations on a localhost project. This tool blocks until pending annotations appear, then r...

DESTRUCTIVE 2 tools

Destructive delete_annotation Permanently removes a specific annotation after successfully implementing the requested change or fix. IMPO... Destructive delete_project_annotations Batch delete ALL annotations for a specific project after successfully implementing all requested changes. ...

// RUNNING THIS SERVER

The managed route: connect Vibe Annotations Server through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y vibe-annotations-server

// FAQ

How many tools does the Vibe Annotations Server MCP server have? +

The Vibe Annotations Server MCP server exposes 6 tools across 2 categories: Read, Destructive.

How do I enforce policies on Vibe Annotations Server tools? +

Route the Vibe Annotations Server server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Vibe Annotations Server tools fall into? +

Vibe Annotations Server tools are categorised as Read (4), Destructive (2). Each category has a recommended default policy.

Enforce policy on every Vibe Annotations Server tool call.

Start from Vibe Annotations Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Instant setup, no code required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.