mcp_servers
Verified Safeby FractalizeR
Overview
Enables AI agents to create, read, update, and delete content (pages, dynamic tables, and resources) within Yandex Wiki for documentation management, knowledge base creation, and structured data handling.
Installation
npx mcp-server-yandex-wikiEnvironment Variables
- YANDEX_WIKI_TOKEN
- YANDEX_ORG_ID
- YANDEX_CLOUD_ORG_ID
Security Notes
The server securely handles Yandex Wiki OAuth tokens and Organization IDs exclusively via environment variables, with explicit validation and error handling for missing credentials. No hardcoded secrets are present in the provided source code. It utilizes a robust HTTP client with retry mechanisms and error mapping for API interactions. Dependency auditing (Socket.dev, Gitleaks) is integrated into the build process, indicating a focus on supply-chain security. The CLI components handle client configuration files securely by only persisting 'safe' fields and not sensitive tokens. While tools inherently interact with external APIs, and potential prompt injection leading to unintended API calls is a general LLM risk, sensitive write operations in tool metadata are flagged with `requiresExplicitUserConsent: true` to indicate they are dangerous and should prompt user confirmation in a capable client.
Similar Servers
mcp-server
Provides a Model Context Protocol (MCP) server for AI agents to search and retrieve curated documentation for the Strands Agents framework, facilitating AI coding assistance.
google-docs-mcp
Provides a comprehensive Model Context Protocol (MCP) server that enables AI assistants to programmatically interact with Google Docs (reading, writing, formatting, structuring) and manage Google Drive files (discovery, folder management, file operations, document creation).
pluggedin-app
A testing environment for MCP (Model Context Protocol) servers, enabling interaction via a chat interface powered by Large Language Models (LLMs) and LangChain ReAct framework.
MediaWiki-MCP-Server
An MCP server that enables Large Language Model (LLM) clients to interact with any MediaWiki wiki.