mcp-memory-server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Memory Server
Persistent agent memory for Blockbrain (or any MCP client) via Markdown files + SQLite FTS5 full-text search.
Why?
Blockbrain agents don't persist memory between sessions. Every conversation starts from zero. This MCP server fixes that — the agent can save what it learned and recall it next time.
How it works:
Agent solves a problem → calls
memory_savewith the solutionAgent starts a new task → calls
memory_recallto check for similar past problemsAll memories are stored as readable Markdown files + indexed in SQLite for fast search
Related MCP server: universal-memory-mcp
Tools
Tool | Description |
| Store a memory entry (topic, title, content) |
| Search memories by keyword/topic (FTS5) |
| List all stored topics with entry counts |
| Remove a memory entry by ID |
Quick Start (Docker)
# 1. Clone
git clone https://github.com/lanlibbi/mcp-memory-server.git
cd mcp-memory-server
# 2. Configure
cp .env.example .env
# Edit .env — set MEMORY_API_KEY!
# Generate a key: openssl rand -hex 32
# 3. Run
docker compose up -d
# 4. Verify
curl http://localhost:8080/healthBlockbrain Integration
Expose the server publicly — Blockbrain needs an HTTPS URL:
Option A: Cloudflare Tunnel (
cloudflared tunnel --url http://localhost:8080)Option B: Any reverse proxy (nginx, Caddy, Traefik) with TLS
Option C: ngrok for testing (
ngrok http 8080)
Register in Blockbrain:
Go to Admin → Agents → MCP Servers
Click "+ Add MCP Server"
Fill in:
Name: Memory Server
Server URL:
https://<your-public-url>/sseTransport: SSE
Authentication: API Key
API Key: (the value from your .env)
Save & activate
Assign to an agent and add instructions to the agent's system prompt:
Before starting a new task, call memory_recall with keywords related to the task. After completing a task or learning something new, call memory_save with: - topic: a category for the task (e.g. "contract-review", "supplier-issue") - title: a short descriptive title - content: what was the problem, what was the solution, what was learned
Configuration
All config via environment variables:
Variable | Default | Description |
| (empty = no auth) | API key for X-API-Key header |
|
| Where Markdown files are stored |
|
| HTTP port |
|
| Max search results per query |
|
| debug, info, warning, error |
Storage
Memories are stored as Markdown files with YAML frontmatter:
/data/memories/
├── contract-review/
│ ├── nda-standard-clauses.md
│ └── liability-clause-fix.md
├── supplier-issue/
│ └── delayed-delivery-workaround.md
└── memory.db ← SQLite FTS5 indexEach file looks like:
---
id: a1b2c3d4e5f67890
topic: contract-review
title: NDA Standard Clauses
created_at: 2026-08-20T15:00:00Z
updated_at: 2026-08-20T15:00:00Z
---
# NDA Standard Clauses
The standard NDA should always include...You can browse, edit, or delete memories directly — they're just Markdown files. The SQLite index stays in sync automatically.
Local Development (without Docker)
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
export MEMORY_API_KEY=test-key
export MEMORY_DATA_DIR=./data/memories
python -m uvicorn src.server:app --host 0.0.0.0 --port 8080API Endpoints
Endpoint | Method | Description |
| GET | Health check (no auth required) |
| GET | SSE endpoint for MCP client connection |
| POST | MCP message endpoint (used by SSE transport) |
Tech Stack
Python 3.12 + MCP SDK
Starlette + Uvicorn for HTTP/SSE
SQLite FTS5 for full-text search (zero external dependencies)
Markdown for human-readable storage
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted MCP memory for coding agents: persistent across sessions, editable markdown, team sharing.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server providing persistent memory management for AI agents using SQLite and FTS5, enabling storage, full-text search, and recall of memories with namespace isolation.1MIT
- AlicenseAqualityNot gradedmaintenancePersistent memory MCP server for AI agents, using SQLite with hybrid keyword and semantic search for long-term memory storage.5Do What The F*ck You Want To Public
- AlicenseNot gradedqualityDmaintenancePersistent memory MCP server that stores and retrieves memories in Markdown files, enabling shared context across multiple AI agents with hybrid search and deduplication.MIT
- AlicenseAqualityBmaintenanceMCP server for persistent, cross-session, local-first memory for AI agents, storing memories as Markdown files with SQLite indexing for hybrid search.24Apache 2.0