mcp-server
Verified Safeby contextstream
Overview
Provides persistent memory, semantic search, and code intelligence to AI coding tools (e.g., Cursor, Claude Code, VS Code) by acting as an MCP server proxy to the ContextStream API, enabling AI to 'remember' context across sessions and tools.
Installation
npx -y @contextstream/mcp-serverEnvironment Variables
- CONTEXTSTREAM_API_URL
- CONTEXTSTREAM_API_KEY
- CONTEXTSTREAM_JWT
- CONTEXTSTREAM_WORKSPACE_ID
- CONTEXTSTREAM_PROJECT_ID
- CONTEXTSTREAM_USER_AGENT
Security Notes
The server correctly handles API keys/JWTs via environment variables, avoiding hardcoded secrets. Network requests are made using standard `fetch` with retries and timeouts, and a specific user agent is set. File system operations are localized to `.contextstream/config.json` in the project root and `~/.contextstream-mappings.json` globally, as well as reading project files for indexing. File reading for ingestion includes explicit ignore lists for common sensitive directories/files (`node_modules`, `.git`, lock files) and a maximum file size limit (1MB), mitigating risks of accidental data exposure or excessive resource consumption. No `eval` or similar dynamic code execution vulnerabilities were found. Overall, the server appears well-designed for security within its intended scope as a local client-side agent.
Similar Servers
CodeGraphContext
An MCP server that indexes local code into a Neo4j graph database to provide real-time, accurate context and relationship analysis to AI assistants for understanding, writing, and refactoring code.
memory-graph
Provides intelligent, persistent graph-based memory capabilities for AI assistants and coding agents in Claude Code environments.
In-Memoria
Provides persistent intelligence infrastructure (semantic concepts, patterns, architecture) for AI agents to understand and interact with codebases.
mcp-memory-keeper
Provides persistent context management for Claude AI coding assistants, ensuring work history, decisions, and progress are preserved across sessions and context limits.