Memory MCP
A persistent, cross-provider memory server that stores user facts in Postgres and exposes search and upsert tools for any MCP-capable agent.
README
Memory MCP
A persistent, cross-provider memory server using FastMCP, Langchain, and Postgres.
Features
- MCP Server that agents can use to store facts about the user
- Transferrable across providers - usable across multiple agents
- Compatible with any MCP-capable agent (Claude Desktop, Claude Code, Opencode, etc.)
- Backed by Postgres to ensure data persistence and scalability
- Support multiple users from a single server
- Exposes two tools to your agent:
search_memory: Search the database for memories about the userupsert_memory: Add/update memories for the user
Prerequisites
- Docker/Podman compose
- Openshift CLI
Usage
Local
-
Clone the repository:
git clone https://github.com/taagarwa-rh/memory_mcp.git cd memory_mcp -
Spin up the services:
# For Podman podman compose up -d # For Docker docker compose up -dThe MCP server will now be available at
http://localhost:1313/mcp
Openshift
-
(Optional) Update the postgres username and password in secret.yaml
-
Deploy the resources
oc apply -n <your-namespace> -f deploy -
Fetch the route:
ROUTE=$(oc get route memory-mcp -o jsonpath='{.spec.host}') ROUTE="https://$ROUTE/mcp" echo $ROUTE
Connect to Agents
Claude Desktop
{
"mcpServers": {
"memory": {
"transport": "http",
"url": "<mcp-route>",
"headers": {
"X-User-Id": "your_user_id"
}
}
}
}
Claude Code
claude mcp add --transport http memory https://<mcp-route>/mcp --header "X-User-Id: <your-username>"
OpenCode
opencode mcp add
Location: Either Name: memory Type: Remote URL: https://<mcp-route>/mcp
Then in your opencode.json, add the user ID header:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"memory": {
"type": "remote",
"url": "https://<mcp-route>/mcp",
"headers": {
"X-User-Id": "<your-username>"
}
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.