Structured Memory

Created By
nmeierpolys10 months ago
Make it easy for agents to build their context about your projects over time The server provides a set of tools to help agents accumulate knowledge about a project over time in a structured way. These memory documents represent living documents that grow and evolve rich context to help the MCP client better serve requests in that area. Memory documents are stored as markdown files in the filesystem, allowing direct access and editing if you want to take a more hands-on approach. The main focus, though, is on giving the MCP client a place to deliberately keep track of info that will be helpful in the future.
Overview

What is Structured Memory?

Structured Memory is a Model Context Protocol (MCP) server designed to help agents accumulate and manage knowledge about projects over time in a structured manner. It allows for the creation of living documents that evolve with rich context, aiding the MCP client in serving requests effectively.

How to use Structured Memory?

To use Structured Memory, you can create a memory document for your project by asking your LLM client. The memory document will start empty and grow as you interact with it. You can also manually update the markdown files stored in the filesystem.

Key features of Structured Memory?

  • Creation of structured memory documents that evolve over time.
  • Markdown file storage for easy access and editing.
  • Automatic updates by the LLM based on conversations.
  • Tools for creating, listing, and updating memory documents.

Use cases of Structured Memory?

  1. Travel planning with detailed itineraries and preferences.
  2. Research projects that require organized data and findings.
  3. Real estate searches with listings and market insights.
  4. Career development tracking and planning.

FAQ from Structured Memory?

  • Can I edit the memory documents manually?

Yes! Memory documents are stored as markdown files, allowing for direct access and editing.

  • How does the LLM update the memory?

The LLM learns from your conversations and automatically updates the memory document with relevant information.

  • What types of projects can benefit from Structured Memory?

Any project that requires ongoing context accumulation, such as travel, research, or product planning.

Server Config

{
  "mcpServers": {
    "mcp-structured-memory": {
      "command": "npx",
      "args": [
        "@nmeierpolys/mcp-structured-memory"
      ]
    }
  }
}
Project Info
Created At
10 months ago
Updated At
10 months ago
Author Name
nmeierpolys
Star
-
Language
-
License
-

Recommend Servers

View All
Payai X402 Tools

8 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

a day ago