Manages contextual boundaries for AI agents based on defined roles.
Manages contextual boundaries for AI agents based on defined roles.
A Model Context Protocol (MCP) server that defines and governs contextual boundaries based on agent roles in your system.
This MCP server enables role-based context management for AI agents, allowing you to:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| process-with-role | Process a query using a specific role |
| create-role | Create a new role |
| update-role | Update an existing role |
| delete-role | Delete a custom role |
| change-role-tone | Change the tone of a role |
| store-memory | Store a memory for a specific role |
| clear-role-memories | Clear all memories for a role |
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Planning and orchestration for AI-driven software development
Read-only MCP for the Eco game wiki: search, Markdown pages, and wiki_ lookups. No keys, no writes.
A Ghidra plugin that provides a bridge between Ghidra and a Zig-based MCP server for enhanced program analysis capabilities.
Local-first engineering cognition for AI coding agents — persistent memory over your codebase.