uml-memory
MCP server for Unified Memory Layer — persistent memory across AI coding tools.
Quick Start
pip install uml-memory
Add to your MCP config (~/.cursor/mcp.json for Cursor):
{
"mcpServers": {
"uml": {
"command": "uvx",
"args": ["uml-memory"],
"env": {
"UML_API_URL": "https://your-server.com",
"UML_API_TOKEN": "your-token-here"
}
}
}
}
Restart your IDE. The MCP tools will appear automatically.
What It Does
Once configured, your AI coding agent will automatically:
- Compose context at the start of every task (loads relevant decisions, constraints, and patterns)
- Save memories when important decisions or insights emerge during conversations
- Check lessons learned before risky operations like deployments or migrations
Available Tools
| Tool | Description |
|---|---|
uml_compose |
Load relevant context at the start of a task |
uml_save_memory |
Save a decision, constraint, or insight |
uml_search |
Search memories by keyword or meaning |
uml_list_projects |
List all projects with saved memories |
uml_save_conversation |
Extract insights from a conversation |
uml_detect_memories |
Analyze text for high-value content |
uml_check_lessons |
Check lessons learned before risky operations |
uml_generate_rules |
Generate AGENTS.md or .cursor/rules from memories |
uml_import_transcript |
Import conversation transcripts |
Getting Your Token
- Log in to your UML instance
- Go to Settings
- Click Generate API Token
- Copy the token into your
mcp.json
Metadata
Release files for uml-memory 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| uml_memory-0.2.0.tar.gz | 8.3 kB | Without provenance | Details for uml_memory-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| uml_memory-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for uml_memory-0.2.0-py3-none-any.whl |
Total release size: 17.5 kB
Release files / uml_memory-0.2.0.tar.gz
| Download URL | uml_memory-0.2.0.tar.gz |
|---|---|
| Size | 8.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f7ecfd4ce24d419f0ef4f42f66f901558458687e94d32f84a4ed86a9c6132155
|
|
BLAKE2b-256 checksum How to use checksums |
94d7dc1e57f42d0daa4e801b12e99b50af210c1315838cf3a01348a3d162a37a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Release files / uml_memory-0.2.0-py3-none-any.whl
| Download URL | uml_memory-0.2.0-py3-none-any.whl |
|---|---|
| Size | 9.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
086cdad1b4dd7ce07b3e0228207f9d5bdd7c276cca863f4638acbfdf33ccca7c
|
|
BLAKE2b-256 checksum How to use checksums |
6fd8193824979a202efaeb883fb0a1547cafc016283ba8e20fcb76e870f3834d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.7
|
Security for uml-memory 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.