MCP Memory Service
MCP server by doobidoo
Store and search persistent semantic memory with a knowledge graph, shared across agents, sessions and AI clients.
Install MCP Memory Service
Runs on your machine. Your client starts it with this command:
Needs uv (Python) on your computer. The setup steps below show where the command goes in each client.
Share this server
Opens this page, with the install command and setup steps.
mcp.tc/i/mcp-memory-serviceAbout
MCP Memory Service is a self-hosted memory backend for AI assistants and agent pipelines. It stores decisions, project context and code patterns, and retrieves them by semantic search. A knowledge graph links memories with typed relationships, and a consolidation step compresses older memories. Embeddings run locally via ONNX.
It runs locally over stdio with uvx (uvx --from mcp-memory-service memory server) or pip install mcp-memory-service. The same service can also run as an HTTP server with a REST API and web dashboard (memory server --http). Storage backends include SQLite, Cloudflare, Hybrid and Milvus. No API key is needed for local use.
What you can do
- Store memories that persist across sessions and agents
- Search memories by semantic similarity
- Filter memories by tags with AND/OR matching
- Link memories in a knowledge graph with typed edges
- Consolidate older memories automatically
- Use the REST API and web dashboard in HTTP mode
- Tag memories by agent identity with the X-Agent-ID header
Tools
Local servers list their tools once they’re running, so we can’t show them here. Look for the list in its documentation; your client shows them after you add it.
Example prompts
Remember that we chose SQLite for this project because of single-user deployment.
Search my memory for past decisions about the authentication design.
Find memories tagged architecture and database.
What did we decide last week about the API versioning?
Set up
Every client starts MCP Memory Service on your machine with the same command. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport stdio mcp-memory-service -- uvx --from mcp-memory-service memory server- Start Claude Code and type
/mcp. mcp-memory-service should show as connected.
Add --scope user to make it available in every project.
Claude Desktop
- Open Settings → Developer → Edit Config. It opens
claude_desktop_config.json. Add:
{
"mcpServers": {
"mcp-memory-service": {
"command": "uvx",
"args": [
"--from",
"mcp-memory-service",
"memory",
"server"
]
}
}
}- Save the file and restart Claude Desktop.
Needs uv (Python) on your computer. The file lives in ~/Library/Application Support/Claude/ on macOS and %APPDATA%\Claude\ on Windows.
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"mcp-memory-service": {
"command": "uvx",
"args": [
"--from",
"mcp-memory-service",
"memory",
"server"
]
}
}
}Needs uv (Python) on your computer.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"mcp-memory-service","type":"stdio","command":"uvx","args":["--from","mcp-memory-service","memory","server"]}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"mcp-memory-service": {
"type": "stdio",
"command": "uvx",
"args": [
"--from",
"mcp-memory-service",
"memory",
"server"
]
}
}
}Needs uv (Python) on your computer.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"mcp-memory-service": {
"command": "uvx",
"args": [
"--from",
"mcp-memory-service",
"memory",
"server"
]
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf.
Codex
codex mcp add mcp-memory-service -- uvx --from mcp-memory-service memory serverOr edit ~/.codex/config.toml directly:
[mcp_servers.mcp-memory-service]
command = "uvx"
args = ["--from", "mcp-memory-service", "memory", "server"]Needs uv (Python) on your computer.
Gemini CLI
gemini mcp add mcp-memory-service uvx -- --from mcp-memory-service memory serverThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients that start local servers accept this shape:
{
"mcpServers": {
"mcp-memory-service": {
"command": "uvx",
"args": [
"--from",
"mcp-memory-service",
"memory",
"server"
]
}
}
}Zed puts servers under context_servers in its settings, with the same command, args and env fields.
Needs uv (Python) on your computer.
Embed
Show MCP Memory Service in a README or on your site. Each embed links to this page, uses the server’s own install command, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/mcp-memory-service)<a href="https://mcp.tc/i/mcp-memory-service"><img src="https://mcp.tc/i/mcp-memory-service/badge.svg" alt="MCP Memory Service on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/mcp-memory-service.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/mcp-memory-service" title="MCP Memory Service on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, install command, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/mcp-memory-service.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the MCP Memory Service card to your site.
Add the mcp.tc card for MCP Memory Service, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/mcp-memory-service.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="mcp-memory-service"><a href="https://mcp.tc/i/mcp-memory-service">MCP Memory Service on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/mcp-memory-service)
```
Reference: https://mcp.tc/embedChange history
This server runs on your computer, so we follow its PyPI package: each new version shows up here, with edits by its owner.
-
New version 12.11.0 (was 12.10.0). Read from PyPI.
-
New version 12.10.0 (was 12.9.0). Read from PyPI.
-
New version 12.9.0 (was 12.8.0). Read from PyPI.
-
New version 12.8.0 (was 12.7.0). Read from PyPI.
-
New version 12.7.0 (was 12.6.0). Read from PyPI.
-
New version 12.6.0 (was 12.5.0). Read from PyPI.
-
New version 12.5.0 (was 12.4.0). Read from PyPI.
-
New version 12.4.0 (was 12.3.1). Read from PyPI.
-
New version 12.3.1 (was 12.2.1). Read from PyPI.
-
New version 12.2.1 (was 12.1.1). Read from PyPI.
-
New version 12.0.1 (was 12.0.0). Read from PyPI.
-
New version 12.0.0 (was 11.15.0). Read from PyPI.
-
Tracking started: version 11.15.0.
FAQ
Can I paste mcp.tc/i/mcp-memory-service into my MCP client?
No. MCP Memory Service runs on your own computer, started by your client, so it has no web address to connect to. The quick link is the page to share; the install command is uvx --from mcp-memory-service memory server.
Does MCP Memory Service need an API key?
No. It doesn’t declare any keys or environment variables. It runs with your user account’s permissions, so check what its tools can reach.
Is MCP Memory Service a remote or a local server?
Local. Your client starts it as a process on your computer with uvx --from mcp-memory-service memory server, which needs uv (Python).
What can MCP Memory Service do?
You can store memories that persist across sessions and agents, search memories by semantic similarity and filter memories by tags with AND/OR matching.
Which clients can use it?
Any client that starts local servers: Claude Code, Claude Desktop, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. claude.ai and ChatGPT only connect to remote servers.
Does mcp.tc track changes to MCP Memory Service?
Partly. It runs on your computer, so we follow its PyPI package: its History tab shows each new version and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read MCP Memory Service’s public metadata (its package and repository pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with doobidoo. This page was built from MCP Memory Service’s public metadata, last checked on 3 Oct 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.