Unforget MCP Server
Long-term memory for Claude Code, Cursor, and any MCP client. Zero LLM on write. Zero config.
Install
pipx install unforget-mcp --python python3.12
Setup
Claude Code
Add to your project's .mcp.json or global settings:
{
"mcpServers": {
"unforget": {
"command": "unforget-mcp",
"args": []
}
}
}
Cursor
Add to Cursor settings → MCP Servers:
{
"mcpServers": {
"unforget": {
"command": "unforget-mcp",
"args": []
}
}
}
VS Code (Copilot)
Add to .vscode/mcp.json:
{
"mcpServers": {
"unforget": {
"command": "unforget-mcp",
"args": []
}
}
}
That's it. No API keys, no Docker, no database setup. An embedded PostgreSQL starts automatically.
Tools
| Tool | Description |
|---|---|
memory_store |
Store a fact, preference, or decision |
memory_search |
Search memories with 4-channel retrieval |
memory_forget |
Delete memories by query or ID |
memory_list |
List all stored memories |
memory_update |
Update a memory (preserves history) |
Options
# Embedded mode (default — auto-starts PostgreSQL)
unforget-mcp
# External database
unforget-mcp --database-url postgresql://user:pass@localhost/db
# Custom scoping
unforget-mcp --org-id myorg --agent-id myagent
# SSE transport (for remote connections)
unforget-mcp --transport sse --port 8767
How It Works
Claude Code / Cursor / MCP Client
│ MCP protocol (stdio or SSE)
▼
unforget-mcp server
├── unforget core (4-channel retrieval, embedder, reranker)
└── pgserver (embedded PostgreSQL + pgvector)
- Memories persist in
~/.unforget/mcp-data/ - 4-channel retrieval: semantic + BM25 + entity + temporal
- Cross-encoder reranking for accuracy
- Zero LLM calls on write (~7ms per memory)
License
Apache 2.0
Metadata
Release files for unforget-mcp 0.1.0
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 |
|---|---|---|---|---|
| unforget_mcp-0.1.0.tar.gz | 4.7 kB | With provenance | Details for unforget_mcp-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| unforget_mcp-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for unforget_mcp-0.1.0-py3-none-any.whl |
Total release size: 10.1 kB
Release files / unforget_mcp-0.1.0.tar.gz
| Download URL | unforget_mcp-0.1.0.tar.gz |
|---|---|
| Size | 4.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c16f9deab296526a00782d94d8f315868bf9efe40060c8f8ca70e19eb614ab76
|
|
BLAKE2b-256 checksum How to use checksums |
7fa38086baf5f6820323002481ea349d186fd5e17ab2c4db13c82efbcc8c13d2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 29, 2026.
Transparency logRelease files / unforget_mcp-0.1.0-py3-none-any.whl
| Download URL | unforget_mcp-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
54270d9255141fdb16fab859e34c2a2f4e815857b7f6cfcb57af608b355d98bd
|
|
BLAKE2b-256 checksum How to use checksums |
0356cbd5a25a75a9198719ddb2ece69c74c14c27e68aaac6bb31c242de6060c8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 29, 2026.
Transparency logSecurity for unforget-mcp 0.1.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for unforget_mcp-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 29, 2026.
Transparency logA 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.