Skip to main content
All connectors
qbash Connectors / qbash Memories

qbash Memories MCP serverand Python AI tasks

qbash hosts a qbash Memories MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse.

Developers use qbash Tasks to write cloud-hosted Python functions that pair qbash Memories with models such as Claude and GPT.

Connect qbash Memories free

MCP server

Build a qbash Memories MCP server

Give ChatGPT, Claude and your other AI tools access to qbash Memories through one server. You pick which qbash Memories tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

  1. Connect qbash Memories on the qbash Connectors page.
  2. Create an MCP server and add the qbash Memories tools you want to share.
  3. Paste the server URL into your client. It connects with OAuth or an access token.

Connect a client Package an MCP server

Python AI task

Write a qbash Memories task in Python

A qbash Task is a hosted Python function that calls qbash Memories and AI models.

Draft a renewal brief from saved notes

Search an assigned memory folder for renewal notes, then ask an inline prompt to write a brief that cites each note.

main.py
notes = qbash.memories.search(
    query="renewal review",
    limit=5,
    folder="customer-notes",
)
if notes:
    brief = qbash.ai.run_prompt(
        slug="memories-renewal-brief",
        variables={"notes": json.dumps(notes)},
    )
    qbash.output(brief)
else:
    qbash.output("No renewal notes matched the search.")
Sample search response
[
  {
    "id": "note-1042",
    "name": "Renewal review",
    "content": "Renewal review is due on the first Monday of next month."
  }
]

What the qbash Memories connector can do

  • Case-insensitive keyword search over memory records without using
  • Fetch a memory record by name, or an inline file by stable slug
  • Create a memory record
  • Mark a memory as archived. Idempotent - archiving an
  • Restore an archived memory to active status. Idempotent
  • Block until the memory's embeddings finish (or fail)
  • Semantic search returning [{id, name, content, similarity}]
  • Update an existing memory record by ID
  • Filter records by name or metadata key-value pairs. Omitting the
  • List memory records (lightweight: id, name, created_at, metadata,
  • Get semantic proposition chunks for a record. Omitting the folder
See every qbash Memories method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls qbash Memories, your other connectors and models such as Claude, GPT, Gemini and Grok. qbash hosts and runs it.

AnthropicOpenAIGeminixAI

Run Tasks on a schedule or from your team's tools

OpenAIAnthropicGrokGmailSlackGitHub+ more
  • Deterministic where it counts Write the logic in Python and call a model only for the steps that need judgement, so the rest runs the same way every time.
  • Version controlled Every save is a revision you can compare and roll back.
  • Logged Each run records its inputs, output, errors and what started it.
  • Shared credentials Connections belong to your organization, so a Task keeps working when its author is away.

qbash Tasks Python AI SDK

qbash Memories MCP questions

Do memory writes from an MCP client publish straight away?

Only when the folder allows it. With Require review for writes turned on, create_memory and update_memory submit a proposal that a reviewer accepts in qbash.

Can a Task and an MCP client use the same folder?

Yes. A folder on an MCP server can also be assigned to a Task under an alias in Tools → Memory. Both keep the folder’s qbash permissions and history.

Guides that use qbash Memories

Build a qbash Memories task

Write it in Python with AI steps, and qbash hosts it with versions and run logs.

Build a task

Build a qbash Memories MCP server

Pick the qbash Memories tools to share and connect ChatGPT, Claude or Grok Bot.

Build an MCP server