| FMRS | 51 / 100 · D | 74 / 100 · B | 72 / 100 · B |
|---|
| Reliability | 5 / 20 | 11 / 20 | 10 / 20 |
|---|
| Security and permissions | 12 / 20 | 15 / 20 | 15 / 20 |
|---|
| Maintenance | 11 / 20 | 17 / 20 | 16 / 20 |
|---|
| Documentation | 14 / 20 | 17 / 20 | 17 / 20 |
|---|
| Setup experience | 9 / 20 | 14 / 20 | 14 / 20 |
|---|
| Best for | - Teams comfortable with TypeScript/Next.js who want to build their own agent product on top of this scaffold
- Developers evaluating or demoing MCP dynamic tool loading and human-in-the-loop approval patterns
- Deployments with existing PostgreSQL/Docker infrastructure willing to self-host a full stack app
| - Developers needing quick, API-key-free web search capabilities
- Privacy-conscious users who prefer local search execution
- AI application development with Claude Desktop or Claude Code
| - Privacy-conscious developers who want local data storage.
- Researchers who need AI-assisted management of large note collections.
- Users of Markdown editors like Obsidian.
|
|---|
| Not for | - Users who just want to plug a single 'tool server' into Claude Desktop or another MCP client — this project is not that kind of drop-in MCP server
- Users unwilling to operate a database, object storage, and a full front/back-end stack themselves
- Use cases requiring official LangChain- or MCP-protocol-team maintenance and support guarantees
| - Enterprise applications requiring high-scale, reliable search APIs
- Users needing advanced search features like custom ranking or filters
- Accessing sites blocked by TLS fingerprinting without installing the optional browser backend
| - Users needing cloud sync and mobile access (unless using the paid cloud service).
- Minimalists who want zero configuration.
- Scenarios requiring large-scale vector databases and complex retrieval (local SQLite may be insufficient).
|
|---|
| Required permissions | - Database read/write access (PostgreSQL) for conversation history and stored MCP server configs
- Object storage read/write access (S3-compatible storage / MinIO) for file uploads
- Outbound network access to call OpenAI/Google/Anthropic model APIs
- Ability to execute local commands or reach remote HTTP endpoints as configured by the user when they register stdio/HTTP MCP servers
| - Outbound network access to DuckDuckGo and other websites
- Reads environment variables for SafeSearch, region, and CA certificates
- Optionally reads a CA certificate file (for TLS-intercepting proxies)
| - Read and write to the local filesystem (default: ~/basic-memory).
- Perform file and directory operations (create, edit, delete).
- Access local SQLite database (or Postgres/Milvus if configured).
|
|---|
| Risks and side effects | - Users can register arbitrary stdio commands as MCP servers via the settings UI; trusting an unverified command can lead to local command execution
- An optional 'auto-approval' mode skips the human-in-the-loop review of tool calls, amplifying the impact of mistaken or malicious tool invocations
- API keys and database connection strings are stored as environment variables and must be protected (`.env.local`)
- The app exposes an OpenAPI explorer at `/api-docs`, so production access controls should be reviewed
| - Search endpoints may occasionally return empty results or errors, especially when blocked
- Content fetching may be subject to SSRF protection, blocking private or loopback addresses by default
- Misuse could lead to rate limiting or IP blocking
| - Tools have write operations that may unintentionally modify or delete notes.
- Edit operations may overwrite existing content, though there are protections.
- Semantic search and reranking features may require model downloads, adding latency.
- Local data backups are the user's responsibility.
|
|---|
| Supported clients | | Claude Desktop, Claude Code | Claude Desktop, Claude Code, Codex CLI, Cursor, VS Code, ChatGPT, Obsidian |
|---|
| Tools | 0 | 2 | 21 |
|---|