mempalace-mcp-http
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mempalace-mcp-httpadd a memory about quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mempalace-mcp-http
HTTP transport for mempalace-mcp. One palace, many machines.
Prerequisites
mempalace must already be installed on the target machine:
uv tool install mempalace # or: pip install mempalaceThis tool extends mempalace — does not replace or install it.
Related MCP server: Levitate
Setup
curl -fsSL https://raw.githubusercontent.com/flejz/mempalace-mcp-http/master/setup.sh | bashOr clone and run:
git clone https://github.com/flejz/mempalace-mcp-http
cd mempalace-mcp-http
./setup.shDetects mempalace, installs HTTP deps, configures systemd service. If ~/.claude/settings.json exists, prompts to add (or replace existing mempalace entry with) the HTTP MCP config automatically.
Token management
mempalace-token is installed to ~/.local/bin/ during setup:
mempalace-token show # masked preview
mempalace-token reveal # full token
mempalace-token rotate # new token + restart service
mempalace-token remove # invalidate token — blocks all clientsremove replaces the token with an unguessable value (server stays auth-required, no valid token exists). Use rotate to recover access.
Claude Code config
Setup auto-configures via claude mcp add with a confirmation prompt. Manual command on any machine:
claude mcp add --transport http mempalace \
http://<palace-host>:8765/mcp \
--header "Authorization: Bearer <token>"Replaces the standard stdio entry (python -m mempalace.mcp_server) — setup.sh detects it and prompts automatically.
For non-Claude clients, equivalent settings.json entry:
{
"mcpServers": {
"mempalace": {
"type": "http",
"url": "http://<palace-host>:8765/mcp",
"headers": { "Authorization": "Bearer <token>" }
}
}
}Env vars
Var | Default | Purpose |
|
| Listen port |
|
| Bind address |
| (unset = open) | Bearer auth token |
How it works
Calls
mempalace.mcp_server.handle_request()directly — no subprocess, no protocol proxyingthreading.Lockserializes all calls — sqlite-safe under concurrent clients1:1 tool mapping — all mempalace tools available, auto-updated when mempalace upgrades
Health check
curl http://localhost:8765/health
# {"status":"ok","mempalace":"3.x.x"}This server cannot be deployed
Maintenance
Related MCP Connectors
Host your MCP tool over streamable HTTP in one command.
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceHTTP bridge that exposes MCP tools via POST endpoint, enabling remote LLMs to access local functionality with bearer authentication.-
- AlicenseNot gradedqualityAmaintenanceLifts local stdio MCP servers into remote Streamable HTTP endpoints for cloud-hosted AI clients, with bearer-token auth and tool policy filtering.9 npmMIT
- FlicenseNot gradedqualityCmaintenanceExposes mempalace memory tools over HTTP MCP for agent consumption.-
- FlicenseNot gradedqualityBmaintenanceEnables remote MCP clients to securely access AgentMemory tools like memory_recall, memory_smart_search, and memory_save through OAuth 2.1 and Streamable HTTP, while keeping the AgentMemory backend secret private.-