S10.1: Spike: MCP server setup

Open
  • Is something wrong?
#152 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
48/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Active
Tech stack
python
Domain
ai

Research direction

Start with the roadmap entry for S10.1 and the dependency S4.4 (#125); the issue identifies backend/app/mcp/ as the server location. Build and verify the one-tool server with the official MCP Python SDK using MCP Inspector and a desktop client, then record the D7 connection decision. Done means all three acceptance criteria are met.

Written by the indexing model from the issue text.

Description

area: ai priority: P0 spike

Roadmap story S10.1 · Project · Roadmap

Parent epic: E10 #103

Dependencies: S4.4 #125

Priority: P0 · Size: S · Sprint: 7 · Milestone: M6 · Area: ai · Depends on: S4.4 · Reqs: FR-AI1 · Status: Backlog

Story: As a developer, I want a minimal MCP server working end to end, so that we learn the SDK and choose how the web assistant will connect to it.

Acceptance criteria

  • A server built with the official MCP Python SDK in backend/app/mcp/ exposes get_macro_as_of over stdio.
  • The tool works from MCP Inspector and from a desktop MCP client such as Claude Desktop or Claude Code.
  • A decision is recorded on how the web assistant reaches the tools (D7): same-process function calls, or the MCP server over Streamable HTTP.

Tasks

  • Add the SDK and a one-tool server
  • Test it with MCP Inspector and a desktop client
  • Record D7

Progress evidence (2026-11-08): No implementation or completion evidence for these acceptance criteria is present in the audited commit. This remains planned work.

Audited against committed main at 0c32c57. Local, staged, and untracked work is excluded.

Dominant language
Python
Stars
0
Forks
0
Avg merge
3h 33m
Merged PRs (30d)
50

Getting set up

  • No Dockerfile or Docker Compose file
  • Has a pull request template
  • No contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from nfiasco/Quant-Time-Machine

All issues in nfiasco/Quant-Time-Machine

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.