| FMRS | 66 / 100 · C | 75 / 100 · B |
|---|
| Reliability | 11 / 20 | 12 / 20 |
|---|
| Security and permissions | 13 / 20 | 16 / 20 |
|---|
| Maintenance | 13 / 20 | 14 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 14 / 20 | 15 / 20 |
|---|
| Best for | - Individuals planning train travel within China
- Developers who want 12306 query capabilities inside MCP clients such as Claude Desktop or Cursor
- Teams that need a self-hosted remote HTTP MCP service or Docker deployment
- Developers studying MCP server implementations
| - 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 | - Scenarios needing official booking, rebooking, refunds or payment (this project is query-only)
- Commercial use or production systems with availability/SLA requirements
- Mission-critical workloads that cannot tolerate upstream API changes or volatility
- Users expecting official 12306 support or endorsement
| - 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 | - Network access: must be able to reach the official 12306 endpoints
- Local file reads: loads bundled static resources such as station data
- HTTP mode port binding: listens on 0.0.0.0:8000 by default
- Reads a .env file in the project root when used
| - 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 | - Unofficial third-party project that only aggregates and relays 12306 public endpoints; upstream changes or rate limits can break queries
- The README explicitly states it is for learning and research only and prohibits commercial use; users bear the consequences of use
- Binding HTTP to 0.0.0.0 may expose the port to other hosts on the network, and no authentication mechanism is described
- Frequent upstream calls may trigger rate limiting or affect the user's account
- Results depend on upstream data and may be delayed or inaccurate, so they should not be the sole basis for decisions
| - 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, Cursor | 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 | 7 | 14 |
|---|