CacheTank is an AI memory layer that saves your identity, projects, decisions, and knowledge, allowing any AI tool to access this context automatically without re-explaining.
From the registry: CacheTank MCP server gives every AI tool your personal context so you never start from zero.
Please install the `cachetank-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **CacheTank tokens** — Obtain read (and optionally write) tokens from the CacheTank browser extension or cachetank.com. (https://cachetank.com)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","cachetank-mcp"]
- required environment variables:
- `CACHETANK_READ_TOKEN`: CacheTank read token (example: `<your-cachetank-read-token>`)
- optional environment variables:
- `CACHETANK_WRITE_TOKEN`: CacheTank write token — enables saving back to your tank (example: `<your-cachetank-write-token>`)
Note: Also available as a remote HTTP endpoint at https://cachetank-mcp-77926794635.us-central1.run.app/mcp for Claude Connectors.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CACHETANK_READ_TOKENrequiredYour CacheTank read token (get it from the extension or cachetank.com).CACHETANK_WRITE_TOKENEnables saving back to your tank.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.