| FMRS | 55 / 100 · C | 75 / 100 · B |
|---|
| Reliability | 10 / 20 | 12 / 20 |
|---|
| Security and permissions | 9 / 20 | 16 / 20 |
|---|
| Maintenance | 12 / 20 | 14 / 20 |
|---|
| Documentation | 13 / 20 | 18 / 20 |
|---|
| Setup experience | 11 / 20 | 15 / 20 |
|---|
| Best for | - Geotechnical and geomechanics engineers who already have an ITASCA engine installed and want to drive simulations through an AI agent by natural conversation
- Users who frequently need to look up PFC/FLAC/3DEC/MPoint/MassFlow commands and Python API documentation
- Researchers who submit and monitor long-running simulations while iterating on code
- Technical teams using MCP clients such as Claude Code, Codex CLI, or Gemini CLI
| - 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 ITASCA engine installed — the execution tools depend on a local engine and bridge and cannot run simulations on their own
- Users expecting official ITASCA support or certification; this is a community project
- Users looking for browser, database, or cloud-storage capabilities rather than geomechanics simulation
- Users wanting a fully zero-configuration experience — first-time setup requires registering the MCP server and starting the bridge in the engine
| - 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 | - Run uvx locally and download/execute the itasca-mcp package from PyPI
- Execute code in the ITASCA engine's IPython console to start the bridge (addon.py or itasca_mcp_bridge.start())
- Submit code and simulation tasks to the running ITASCA engine through the bridge and read task state and results
- Network access to PyPI at bridge startup to check for and possibly self-upgrade to a newer release
- Read and write MCP client configuration files to register the server
| - 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 | - The execution tools run code and simulations in a real ITASCA engine; wrong commands or parameters can produce incorrect results or consume significant compute time and resources
- The bridge automatically checks PyPI and self-upgrades, pulling in updates without per-update user confirmation, which introduces supply-chain risk
- Documentation browsing reduces but cannot fully eliminate hallucinated commands produced by the model
- Long-running simulations, if not properly monitored or interrupted, can tie up machine resources for a long time
- This is a community project rather than an official ITASCA release, so compatibility and maintenance cadence are not guaranteed by the upstream vendor
| - 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 Code, Codex, Gemini CLI, GitHub Copilot CLI, OpenCode | 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 | 1 | 14 |
|---|