Ask Your Data

An Alexa+ track prototype: a Streamable HTTP MCP server that loads CSV text, filters and aggregates it, and can use Amazon Bedrock to turn query results into a concise answer suitable for speech.

Demo video (2:45): https://youtu.be/7BZU_YJn_fE

Hackathon scope

• Primary track: Alexa+ — self-hosted MCP server implementing MCP spec 2025-11-25 over Streamable HTTP (MCP Python SDK 1.30+; the version is negotiated during the client handshake).

• Mini-challenges targeted: AWS Builder (Amazon Bedrock Converse API integration in bedrock.py) and Open Source (MIT-licensed public project created during the hackathon window).

• Friction encountered during the build is documented in FRICTION_LOG.md.

• The hackathon's official resources page says Alexa+ projects should use open standards for Agent Skills and Streamable HTTP transports. It also describes AWS Builder as an integration of AWS services and Open Source as a contribution made during the hackathon window.

• Verify current deadlines, eligibility, and submission requirements on the official Devpost page; those details can change.

Related MCP server: Excel Analyser MCP

Requirements

• Python 3.11+

• AWS credentials configured through the standard AWS credential chain, or a short-term Bedrock API key, only when invoking the Bedrock answer tool

• Bedrock model access in the selected AWS region

Install and run

python -m venv .venv
source .venv/bin/activate
python -m pip install -e ".[test]"
ask-your-data-mcp

The MCP server uses Streamable HTTP and listens locally on the MCP SDK's default address (typically http://127.0.0.1:8000/mcp). Keep it bound to localhost unless you deliberately configure and secure a remote deployment.

Connect a client

Any MCP client that supports Streamable HTTP can connect to http://127.0.0.1:8000/mcp.

MCP Inspector (browse tools and call them by hand):

npx @modelcontextprotocol/inspector

Choose the Streamable HTTP transport, enter http://127.0.0.1:8000/mcp, click Connect, then open the Tools tab.

VS Code (GitHub Copilot agent mode) — add .vscode/mcp.json:

{
  "servers": {
    "ask-your-data": { "type": "http", "url": "http://127.0.0.1:8000/mcp" }
  }
}

Then ask, for example: "Load data/sample-expenses.csv into ask-your-data and tell me where most of my money went." The agent calls load_dataset, then query (group by category, sum amount), then answer_with_bedrock.

Configure Bedrock

Set an AWS region, model ID, and Bedrock credentials before starting the server. Do not put credentials in this repository.

export AWS_REGION=us-east-1
export BEDROCK_MODEL_ID=your-enabled-bedrock-model-id

For a quick local test, create a short-term API key in the Amazon Bedrock console under API keys. Generate it while the console is set to the same region as AWS_REGION; it expires with your console session (up to 12 hours). In the same terminal where you will start the server, enter the key without echoing it or adding it to shell history:

read -s AWS_BEARER_TOKEN_BEDROCK
export AWS_BEARER_TOKEN_BEDROCK

Press Enter after pasting the key. Alternatively, configure AWS credentials using the standard AWS credential chain (for example, an IAM Identity Center profile). The model must be available to your account in that region. The server returns an explicit error if Bedrock configuration is missing or the AWS call fails; CSV loading and query tools do not require AWS access.

MCP tools

load_dataset

Pass csv_text containing a header and at least one data row, plus an optional dataset name. CSV is limited to 5 MiB and 100,000 data rows. The dataset is held in memory and is not persisted between server restarts.

query

• filters: list of { "column", "operator", "value" } rules. Operators: eq, ne, gt, gte, lt, lte, and contains.

• group_by: optional column name.

• aggregation: optional count, sum (total), avg (average or mean), min, or max.

• column: required for numeric aggregations; optional for count.

• limit: maximum returned rows/groups (1–1000).

Numeric-looking values are compared numerically; other values are compared case-insensitively for relational/equality filters. contains is case-insensitive. Numeric sum and avg reject nonnumeric values. Numeric min and max are returned as JSON numbers; nonnumeric columns retain text results.

summarize

Returns dataset name, row count, column names, and up to five sample rows.

answer_with_bedrock

Pass a question and optionally query results; if omitted, the most recent query result is used. This tool makes a real Amazon Bedrock Converse API call and therefore requires the AWS configuration above. If Bedrock reports a configuration or service error, the tool logs the error on the server and returns a clearly labeled deterministic response from the query results, naming the group with the largest aggregate when results are grouped. If no query results are available, it asks you to run a query first.

Development

python -m pytest

Current limitations

• One in-memory dataset is shared by all clients connected to this server.

• CSV must be supplied as tool input; no arbitrary local file paths are exposed.

• Bedrock answers need an AWS account with Bedrock inference enabled. The hackathon account used for development was blocked by AWS (see FRICTION_LOG.md), so the demo shows the deterministic fallback answer.

• A web-based Alexa+ simulator and richer spreadsheet formats (XLSX, Google Sheets, S3) are follow-up work.