Memstate + Any MCP Client
Connect Memstate to any agent that supports the Model Context Protocol.
Memstate works with any MCP-compatible AI agent. If your agent isn't listed in our specific guides, follow these universal steps.
Looking for a specific agent?
We have dedicated guides for Claude, Cursor, Cline, Kilo Code, Windsurf, Gemini CLI, and GitHub Copilot.
Get Your API Key
Sign up for free — no credit card required.
Sign Up FreeAlready have an account? Go to API Keys →
Add the MCP Server
Add the following JSON to your agent's MCP configuration file. Replace YOUR_API_KEY_HERE with your key.
{
"mcpServers": {
"memstate": {
"command": "npx",
"args": ["-y", "@memstate/mcp"],
"env": {
"MEMSTATE_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}How to find your agent's MCP config file
Most MCP clients use a JSON file with an mcpServers key. Common locations:
Check your agent's documentation for the exact path. The JSON structure above works for all standard MCP clients.
Add Agent Instructions
Paste these instructions into your agent's memory or instruction file. This tells your agent to use Memstate automatically — loading context before tasks and saving summaries after.
# Memstate MCP - Memory Storage
This project uses Memstate MCP for persistent, versioned memory across sessions.
## REQUIRED: Start and end every task with memory
**BEFORE starting any task**, load relevant context so you don't redo past work or revert intentional decisions. **Prefer targeted retrieval** — do not dump the full memory tree by default.
**Default — search by what you're working on:**
```
memstate_search(query="<task topic>", project_id="<your_project>")
```
**When you know the exact keypath — fetch that subtree only:**
```
memstate_get(project_id="<your_project>", keypath="<subtree>")
```
**Full tree (discovery only):** `memstate_get(project_id="<your_project>")` with **no keypath** returns **every memory** in the project. Use this only when you need to explore the full tree to discover keypaths and values — not as the default before every task.
**AFTER completing any task**, save what you did so the next session has context:
```
memstate_remember(project_id="<your_project>", content="## Task Summary\n- What was done\n- Key decisions made\n- Files modified", source="agent")
```
Reading before tasks and saving after are both important. Skipping them means the next session starts blind.
## Tool reference
| Tool | When to use |
|------|-------------|
| memstate_search | **Default before tasks.** Find relevant memories by meaning. Returns ranked results without flooding context. |
| memstate_get | Fetch a **specific subtree** when you know the keypath. With no keypath, returns the **full project tree** — discovery/exploration only. |
| memstate_remember | **End of every task.** Save markdown summaries, notes, decisions. |
| memstate_set | Store a single key=value fact (e.g. config.port). Not for summaries. |
| memstate_history | View version history of a keypath. |
| memstate_delete | Soft-delete a keypath (history preserved). |
## Project naming
Use a short snake_case name matching your repo or topic (e.g. my_app, api_service). All related memories should share the same project_id.For agents with a rules system (Cline, Kilo, Cursor), create a file called use-memstate-memory.md in your rules directory instead. For agents without rules, paste this at the top of your project's AGENTS.md or equivalent.
Test It — Onboard Your Project
Restart your agent, open a project, and paste this prompt. It will create your first memories and confirm everything is working.
Replace <your_project> with a short name for your repo (e.g. my_app).
I'm onboarding Memstate AI memory for this project. Please:
1. Analyze this codebase and write a concise high-level architecture overview in markdown — covering the main components, tech stack, key directories, and how data flows through the system.
2. Save it to Memstate using: memstate_remember(project_id="<your_project>", content="<the markdown>", source="agent")
3. Then call memstate_search(query="architecture overview", project_id="<your_project>") and show me the results so I can confirm it worked.What to expect
Your agent will analyze the codebase, write an architecture overview, save it to Memstate, then confirm with search results. You'll see structured memories like project.my_app.architecture — this context is now available in every future session automatically.