dbay-mcp

MCP server for DBay — gives AI agents persistent memory and knowledge base across projects, sessions, and devices.

Quick Start

# Claude Code (one command, global)
claude mcp add --scope user dbay -- uvx dbay-mcp

# Other MCP clients (Cursor, Windsurf, Claude Desktop)
# Add to your MCP config (.mcp.json / claude_desktop_config.json):
{
  "mcpServers": {
    "dbay": {
      "command": "uvx",
      "args": ["dbay-mcp"]
    }
  }
}

New to DBay? Install the CLI first: pip install dbay-cli && dbay login

MCP Tools

Memory

AI agents remember your decisions, conventions, credentials, and preferences across sessions.

Tool	Description
`memory_recall`	Semantic search over past decisions, conventions, facts
`memory_ingest`	Store a memory (fact, decision, rejection, convention, procedural, episode)
`memory_list`	Browse memories by type
`memory_delete`	Remove a memory

Knowledge

Search and upload documents to your knowledge base.

Tool	Description
`knowledge_search`	Hybrid vector + BM25 search over documents
`knowledge_upload`	Upload a file (PDF, DOCX, MD) for processing
`knowledge_upload_directory`	Bulk upload a directory
`knowledge_list`	List all knowledge bases

End-to-End Encryption

For privacy-sensitive use cases, create an encrypted memory base. Content is encrypted locally before upload — the server only stores ciphertext.

pip install dbay-cli
dbay login
dbay mem create --encrypted my-private-mem

The MCP server auto-detects encrypted bases and handles encryption/decryption transparently. No changes needed in your AI agent workflow.

Three-factor security: password (local) + config file (portable) + server-stored encrypted DEK. Any single factor leaked cannot decrypt your data.

Configuration

# Login stores credentials in ~/.dbay/config.json
pip install dbay-cli
dbay login

# Switch default memory/knowledge base
dbay mem use my-mem
dbay kb use my-kb

Environment variables override config file:

Variable	Description
`DBAY_API_KEY`	API key (required)
`DBAY_MEMORY_BASE`	Default memory base ID
`DBAY_KNOWLEDGE_BASE`	Default knowledge base ID
`DBAY_ENDPOINT`	API endpoint (default: https://api.dbay.cloud:8443)

Metadata

Release files for dbay-mcp 0.5.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dbay-mcp 0.5.7
File	Size	Uploaded
dbay_mcp-0.5.7.tar.gz	84.8 kB	Apr 29, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for dbay-mcp 0.5.7
File	Interpreter	ABI	Platform	Reset
dbay_mcp-0.5.7-py3-none-any.whl 20.7 kB Apr 29, 2026	Python 3	none	any	Details

Total release size: 105.5 kB

Release files / dbay_mcp-0.5.7.tar.gz

Download URL	dbay_mcp-0.5.7.tar.gz
Size	84.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`23b7e689387cf2d53c8cc5d55439f7b3aefe841240e5430013f41c2c63fbc402`
BLAKE2b-256 checksum How to use checksums	`bf063ed1ac29d72a04273832267130b945616643323d8618192e4215e6fdb9dd`
Upload date	Apr 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.13.5`

Release files / dbay_mcp-0.5.7-py3-none-any.whl

Download URL	dbay_mcp-0.5.7-py3-none-any.whl
Size	20.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`63b659d5d51a7f3bdb9cf126ce658cc988892d47be4751c0445ca676407a6c05`
BLAKE2b-256 checksum How to use checksums	`48943b8f05d806997925607a5e8945da53da8b3ee711bf259ad6bf2af5e47be2`
Upload date	Apr 29, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.13.5`