Agentdb
Self-learning vector memory for AI agents with hybrid retrieval, knowledge graphs, and MCP tools.
This grade comes from an automated MCPSafe scan of the server's JavaScript, TypeScript and Python source on 2026-10-02. It read the whole repository (393 files). It checks for leaked credentials, shell or code injection from function inputs, unsafe deserialization, malware signatures, install-time scripts, and weak password handling. It does not check for path traversal, server-side request forgery, prompt injection in tool descriptions, network exposure, SQL injection, cross-site scripting, or vulnerable dependencies. It has not been manually reviewed, and the code may have changed since the scan.
Excellent Security
Trust Score 89
Trust is stricter than security: it combines reviewed security, MCP capability risk, supply-chain metadata, quality, popularity, freshness, and penalties for unknowns.
- • No reviewed severe vulnerabilities published
- • Healthy maintenance cadence
- • Solid supply-chain metadata
- • Recently scanned
- • No major confidence penalties from available metadata.
Security ScoreA+
Vulnerabilities Found
Quality ScoreC
Maintenance71
Popularity60
Documentation68
Available Documentation
Compatibility67
Features
Supported Transports
Vulnerabilities(0)
This grade comes from an automated scan. Individual findings from automated scans are not published.
READMEAgentdb
View sourceMCPSafe verified server
Verified MCP server restored in the active MCPSafe registry. Weekly scan data is online and the server is available for registry discovery.
Embed Security Badge
Add this badge to your README or documentation
[](https://mcpsafe.org/registry/agentdb)Server Information
- Source
- NPM
- Package
- agentdb
- Version
- 3.0.0-alpha.20
- Language
- go
- License
- MIT
- Transport
- STDIO
- Added
- Aug 2, 2026
- Updated
- Sep 27, 2026