MCP Tools DirectoryAbout this integration
Persistent decision memory for agents — learns which action works in which context
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.2.1
- Package
- banditdb-python
- Last compatibility test
- Not independently tested
Connect your agent
banditdb-pythonPublisher README and manifest were reviewed from hash-pinned captures. The package and integration endpoints were not executed or independently security-audited. Credentialed or mutating operations remain subject to the publisher-documented boundary.
Capabilities: bandit_decision, reward_recording, experiment_management
Connected profiles
Additional details
com.banditdb/mcp
Source ↗ · Checked 2026-09-170.2.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17BANDITDB_URL, BANDITDB_API_KEY
Source ↗ · Checked 2026-09-17banditdb-python
Source ↗ · Checked 2026-09-190.2.0
Source ↗ · Checked 2026-09-19Publisher includes a dedicated section for starting the MCP server.
Source ↗ · Checked 2026-09-19The documented API key can be omitted only when the selected BanditDB server is configured without authentication.
Source ↗ · Checked 2026-09-19The documented client entry launches the banditdb-mcp Python console script.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19