| FMRS | 46 / 100 · D | 75 / 100 · B |
| Reliability | 6 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 |
|---|
| Maintenance | 10 / 20 | 14 / 20 |
|---|
| Documentation | 12 / 20 | 18 / 20 |
|---|
| Setup experience | 10 / 20 | 15 / 20 |
| Best for | - LLM users and analysts who need Brazilian public procurement open data
- Developers using Claude Desktop, Cursor, Continue, Cline/Roo Code, or Zed
- Govtech, compliance, supplier intelligence, and bidding researchers
- Teams wanting keyless, signup-free access to PNCP and CNPJ public data
| - 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 needing Licinexus's proprietary matchmaking engine, supplier scoring, price aggregation, or AI-generated artifacts
- Scenarios requiring an official SLA or paid support (this is a community project, best effort, no SLA)
- Users expecting access to private databases or non-public data
- ChatGPT web users, since the consumer web app does not support MCP stdio
| - 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 to public HTTPS endpoints: PNCP and BrasilAPI (or MinhaReceita)
- Local execution: downloads and runs the npm package @licinexusbr/mcp via npx, using the local npm cache (e.g. ~/.npm/_npx/)
- Process communication: JSON-RPC over stdin/stdout with the MCP client
- In-memory local cache: short-TTL LRU caching of heavy responses
- Optional environment variables: CNPJ_PROVIDER (brasilapi default or minhareceita), LICINEXUS_LOG_LEVEL, LICINEXUS_LANG
- No API keys or account credentials required
| - 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 | - Data comes from public government APIs; PNCP can take 15–30 seconds to respond, and broad queries may time out
- Public data may be delayed, missing, or inconsistent, so LLM output needs human review and should not be the sole basis for legal or bidding decisions
- npx downloads and executes a third-party npm package, so supply-chain risk depends on the trustworthiness of that package's publishing channel
- npx caching may run an older version unless @latest is specified
- Using an absolute npx path from which npx writes a local machine path into your config file
- Debug logging may include query parameters, so avoid exposing sensitive context
| - 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, Continue, Cline, Roo Code, Zed, ChatGPT | 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 | 18 | 14 |