Structured MCP Server

structured.sh · Quick Start · Connect to Claude · MCP Tools · API Reference · Deploy

Remote serverstreamable-httpPython

What is the Structured MCP server?

structured.sh · Quick Start · Connect to Claude · MCP Tools · API Reference · Deploy. Exposed over MCP by the structured mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Structured gives AI agents (and humans) persistent, queryable memory:

Its toolset

Everything the assistant can do here goes through one of these:

  • create_memory"Create a memory for tracking daily sales with fields: date, revenue, units"
  • list_memories"What memories do I have?"
  • describe_memory"Show me the schema for daily_sales"
  • write_memory"Save today's sales: date=2026-04-09, revenue=1250.50, units=42"
  • query_memory"What's the total revenue this month?"
  • store_document"Remember this config for later"
  • get_document"Get the document abc-123"
  • flush_memory"Flush all pending data to disk"
  • delete_memory"Delete the test_data memory"
  • Memories — The Memories tool exposed by this server
  • Query — The Query tool exposed by this server
  • Settings — The Settings tool exposed by this server

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Structured's toolset — create_memory, list_memories, describe_memory and 10 more — is a fair guide to whether it matches your workflow. It is maintained by structured-sh; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Structured's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Structured.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the structured mcp server does with a few real requests.

Available tools

ToolWhat it does
create_memory*"Create a memory for tracking daily sales with fields: date, revenue, units"*
list_memories*"What memories do I have?"*
describe_memory*"Show me the schema for daily_sales"*
write_memory*"Save today's sales: date=2026-04-09, revenue=1250.50, units=42"*
query_memory*"What's the total revenue this month?"*
store_document*"Remember this config for later"*
get_document*"Get the document abc-123"*
flush_memory*"Flush all pending data to disk"*
delete_memory*"Delete the test_data memory"*
MemoriesThe Memories tool exposed by this server.
QueryThe Query tool exposed by this server.
SettingsThe Settings tool exposed by this server.
FilesThe Files tool exposed by this server.

Example prompts to try

  • Use Structured to create memory.
  • Use Structured to list memories.
  • Use Structured to describe memory.

Frequently asked questions

It connects Structured to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (create_memory, list_memories, describe_memory, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Structured directly.