Kaiza MCP Server
Enables secure, audited file operations with LLMs by enforcing implementation plans, restricting writes to approved file scopes, and maintaining a tamper-evident audit log with stub detection.
README
Kaiza MCP Server
A robust, enterprise-grade Model Context Protocol (MCP) server designed for secure, audited file operations. This server acts as a bridge between LLMs and your filesystem, enforcing strict validation plans and maintaining an immutable audit log of all changes.
Features
- Secure File Writing: All
write_fileoperations must be linked to an approved "Implementation Plan" ID. - Scope Enforcement: Writes are restricted to file paths explicitly allowed by the plan's scope.
- Audit Logging: Every successful write operation is cryptographically hashed and chained in
audit-log.jsonl, ensuring a tamper-evident history. - Stub Detection: Automatically rejects code containing placeholder patterns (e.g.,
TODO,FIXME, empty returns) to ensure production readiness. - Read-Only Access: Provides safe
read_fileaccess to repository contents.
Installation
npm install
Running the Server
The server communicates via stdio. It is intended to be run by an MCP client (such as Claude Desktop or an IDE extension).
node server.js
Tools
write_file
Writes content to a file.
- path: Relative path to the file.
- content: The string content to write.
- plan: The ID of the approved Implementation Plan authorizing this change.
read_file
Reads the contents of a file.
- path: Relative path to the file.
list_plans
Lists all currently approved implementation plans (found in docs/plans/*.md).
read_audit_log
Reads the current session's audit log entries.
Architecture
- Core Logic:
core/plan-enforcer.js: Validates operations againstdocs/plans.core/audit-log.js: Manages the append-only hash chain.core/stub-detector.js: Scans content for non-production patterns.
- Transport: Standard Input/Output (
stdio) using@modelcontextprotocol/sdk.
Development
- Configure Plans: Create markdown files in
docs/plans/withID:,STATUS: APPROVED, andSCOPE:headers. - Start Server: Run
node server.jsto see the session ID startup message.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.