| FMRS | 53 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 9 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 |
|---|
| Maintenance | 11 / 20 | 14 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 |
|---|
| Setup experience | 11 / 20 | 15 / 20 |
|---|
| Best for | - Users with OctoPrint, Klipper, Duet, Repetier, Bambu Lab, Prusa, or Creality printers
- Users who want to drive printing and model workflows from an MCP client in natural language
- Technical users needing an end-to-end modify-STL, slice, and print workflow
- Bambu users using FULU OrcaSlicer-bambulab or Bambu Studio as the project slicer
| - Individuals or teams who prioritise privacy and offline operation and do not want data leaving the machine
- Users who share memory across multiple MCP clients such as Claude Code, Claude Desktop, Hermes Agent, OpenClaw, Cursor, Codex and Gemini CLI
- Scenarios that need encrypted storage, a hash-chained audit log and verifiable vault migration
- Users who want low-latency recall, a bundled embedding model and no extra LLM calls inside the memory layer
|
|---|
| Not for | - Users without any supported printer or printer management system
- Users unwilling to provide printer credentials (API keys, access tokens, serial numbers)
- Users expecting to override slicer settings such as layer height or temperature directly from MCP (must be done before generating the 3MF)
- Users expecting complete real-time streaming Bambu status semantics (status reading remains limited)
- Bambu users without Developer Mode and LAN Only Mode enabled or whose printer is not on the same network
| - Users who need cloud multi-device sync or a hosted team memory service; moving between machines means locking the vault and copying the file
- Users who expect the server itself to run an LLM that extracts facts and decides what to remember; Compartment explicitly keeps no LLM inside and leaves that to the host model
- Users who cannot keep a passphrase safe or who need a recovery path if it is lost, since Compartment never generates a password, seed or recovery phrase
- Deployments that require network transports such as SSE or streamable-http; this server is stdio only and opens no ports
|
|---|
| Required permissions | - API key or Bearer token for the printer management system
- Bambu Lab serial number (BAMBU_SERIAL) and access token (BAMBU_TOKEN)
- Network access to the printer's local network (including Bambu MQTT port 8883 and FTPS port 990)
- Read/write access to the local filesystem for STL, G-code, and 3MF files and the temp directory
- Ability to launch external slicer executables (SLICER_PATH) and optionally the FULU bridge command
- Optional MCP_ALLOW_EXECUTABLE_ARG=1 to accept per-call local executable selectors
| - Read and write the vault file under the user's home directory, by default ~/.compartment/memory.vault, and its sibling settings file
- Access the session directory holding the unlock credential (configurable with COMPARTMENT_SESSION_DIR), which also carries the shared embedding process's Unix socket
- Optionally use the macOS keychain (compartment unlock --keychain is an explicit opt-in, and it survives reboots)
- Write or merge an mcpServers entry into each MCP client's own configuration file, taking a byte-exact backup first
- Install a PostToolUse hook for Claude Code that captures memory files the agent writes
- Serve a read-only dashboard on 127.0.0.1 behind a one-time random URL token
|
|---|
| Risks and side effects | - STL operations load entire models into memory; large files (e.g., over 10MB) can cause out-of-memory issues
- Bambu file operations may use unsecured plain FTP, exposing transfers to network eavesdropping
- A wrong Bambu model preset (bambu_model) can generate dangerous G-code and cause the bed to crash into the nozzle and damage the printer
- Allowing per-call executable paths (MCP_ALLOW_EXECUTABLE_ARG) lets untrusted input choose which local program runs; enable only for trusted diagnostics
- Tool output should be treated as untrusted input, so prompt injection is a risk and destructive operations should have human confirmation gates
- Credentials are stored as environment variables in client config, so a leak grants printer control
| - A leaked passphrase means the encrypted content can be decrypted; Compartment generates no recovery phrase and cannot recover a lost passphrase
- Enabling the memory_unlock tool places the passphrase in the model's context, which is why it is off by default
- If a 2FA keyfile is lost, for example a USB stick, the vault cannot be opened even with the passphrase
- `export --plaintext` writes the vault as unencrypted JSONL, so that file must be handled carefully
- Memory content can come from untrusted sources; recall wraps memories with a notice that they are stored data and content can be marked quarantined, but the host agent must still treat memory as data to limit prompt-injection risk
- The capture hook and client integration write into the user's own settings files, although the implementation backs up and merges rather than replacing
|
|---|
| Supported clients | Claude Desktop, Claude Code, Cursor, Codex | Claude Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro |
|---|
| Tools | 23 | 14 |
|---|