// MCP TOOL REFERENCE

CONTEXT SYNC TOOLS

10 tools from the Context Sync MCP Server, categorised by risk level.

// ALL 10 CONTEXT SYNC TOOLS

READ 8 tools

Read context-sync-usage Complete guide on how to use Context Sync effectively as an AI agent Read debugging-context-sync How to debug Context Sync when things go wrong Read git Git repository operations with intelligence. Provides status, context, risk analysis, and code ownership in... Read notion Access your Notion workspace documentation. Use notion.search to find pages, notion.read to view content. E... Read read_file Read a file from the current workspace. Use this to understand code context. Read remember Store important context about the project. Use when the user shares something that matters for future sessi... Read search Search the workspace. Can search by filename pattern or file contents. Use this to discover relevant files ... Read structure Get the file/folder structure of current workspace. Use this to understand project layout.

WRITE 1 tools

Write set_project Initialize a project for context tracking. Detects project type, tech stack, and architecture. Call this on...

EXECUTE 1 tools

Execute recall Get context about the current project. Returns project identity, active work, constraints, problems, and re...

// RUNNING THIS SERVER

The managed route: connect Context Sync 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 @context-sync/server

// FAQ

How many tools does the Context Sync MCP server have? +

The Context Sync MCP server exposes 10 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Context Sync tools? +

Route the Context Sync 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 Context Sync tools fall into? +

Context Sync tools are categorised as Read (8), Write (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.