| FMRS | 51 / 100 · D | 75 / 100 · B |
|---|
| Reliability | 9 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 |
|---|
| Maintenance | 10 / 20 | 14 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 |
|---|
| Setup experience | 10 / 20 | 15 / 20 |
|---|
| Best for | - Individuals who want to view and organize MyFitnessPal food, exercise and weight records in natural language
- macOS Claude Desktop users who are comfortable authenticating with browser cookies
- People automating entries (e.g. inferring fasts from a sleep window plus first-meal timestamp) or correcting logs programmatically
- Technical users who accept a scraping-based approach and know the interface can break
| - 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 | - Production use requiring official support or a stable public API
- Users unwilling to keep session cookies or account credentials on their machine
- Environments on Python 3.13+ or where lxml cannot be built
- MCP clients other than Claude Desktop (only a Claude Desktop config example is documented)
- Anyone who needs to read fasting history — MFP exposes no read endpoint for it
| - 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 | - Read and modify your MyFitnessPal account data (diary, goals, measurements, water, fasting)
- Write to ~/.mfp_mcp/cookies.json (mode 0600; equivalent to a password with full account access)
- On macOS, read each browser's '<Browser> Safe Storage' keychain entry to decrypt its cookie database
- Read browser cookies (Chromium-based or Firefox) or credentials from the MFP_USERNAME / MFP_PASSWORD environment variables
- Optionally read MFP_SECRET_KEY from the environment or OS keychain to decrypt credentials
| - 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 server can modify your diary, goals, measurements and water — mistaken calls change real data
- Session cookies grant full account access and are stored locally in ~/.mfp_mcp/cookies.json; leaking that file is leaking the account
- Storing plain credentials in the client config puts your MyFitnessPal password in plaintext on disk, readable by anything running as your user
- Reads and writes depend on MFP's undocumented interfaces, which can change without notice (the author notes it already happened once)
- Scraping and internal API use may conflict with MyFitnessPal's terms of service
- If MFP_SECRET_KEY is stored alongside the encrypted values in the same config file, the encryption provides little protection
| - 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 Desktop, Claude Code, Hermes Agent, OpenClaw, Cursor, VS Code, Codex, Gemini CLI, Cline, Roo Code, Zed, OpenCode, LM Studio, AnythingLLM, BoltAI, Goose, Kiro |
|---|
| Tools | 20 | 14 |
|---|