This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
This is an MCP server developed in Python using uv that leverages the official MCP Python SDK (https://github.com/modelcontextprotocol/python-sdk) as the context manager for agents. It features asynchronous communication via kafka-python with other servers to adapt and serve real-time context information. Furthermore, it integrates pytest and testcontainers for robust testing support.
Develop the MCP server under a hexagonal architecture (focused on tools and resources).
Allow dynamic updating of context content, which in turn influences agent responses (update commands originate from a logic management server, not part of this repository).
Provide auditing capabilities for agents querying the server to report usage metrics to another management server (the logic manager is OUTSIDE this repository).
Establish a resilient and adaptable structure for dynamic contexts (e.g., programmatic converters, dependency injection, low coupling, etc).
Related MCP server: agentctx
Python (3.14.4) uv (0.12.1) MCP (2.3.0) kafka-python (3.0.12) pytest (9.2.0) testcontainers (4.15.0)
This server cannot be deployed
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Company brain for AI agents — temporal knowledge graph search, exploration, and durable memory.
