Agent lock-in
Every AI agent used to invent its own memory format. Switch agents, lose everything. MCP is the standard interface that ends that.
MCP explainer · August 2026
Model Context Protocol (MCP) is Anthropic’s open standard for connecting AI agents to shared tools and data. An MCP memory server is a server that any MCP-compatible agent can query to remember what has been done in a project. Tramya implements one, locally.
What MCP solves
Every AI agent used to invent its own memory format. Switch agents, lose everything. MCP is the standard interface that ends that.
Files, databases, project memory, docs: MCP lets an agent access all of them through one uniform protocol.
The MCP server decides what the agent sees. You keep control of the source data.
What Tramya adds
The server runs on your machine. Your project data does not go through a third-party cloud.
Queries are scoped to a project. The agent gets what is relevant to the current repo, branch and worktree — not your whole history.
Claude Code writes to it, Codex reads from it, Cursor tomorrow. One memory, many agents.
MCP memory options
| Option | Where it runs | Setup effort | Local-first |
|---|---|---|---|
| Tramya | Your machine | Install app | Yes |
| mem0 (self-hosted) | Your infra | Deploy Postgres + Qdrant | Depends |
| Cloud vendor MCP | Vendor cloud | API key | No |
| Custom Python MCP server | Anywhere | Write it yourself | Depends |
Model Context Protocol is an open standard from Anthropic that lets AI agents talk to shared tools, memory and data through a uniform interface.
No. Install Tramya, enable the MCP server in settings, point your Claude Code (or other MCP client) at it.
No. MCP is a protocol, not a service. Tramya as an MCP server runs on your machine and speaks the protocol locally.
Claude Code has full support. Other agents are adopting it progressively; check each agent’s docs for status.