microsoft / microsoft/dcp

DCP as MCP (Model Context Protocol) server

Open
#22 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area-orchestrator investigate
Dominant language
Go
Stars
189
Forks
24
Avg merge
2d 16h
Merged PRs (30d)
18

Description

The idea here is to explore the idea of making DCP a Model Context Protocol (https://modelcontextprotocol.io/docs/concepts/architecture) server and make DCP model, model (Executable, Container) history (when https://github.com/microsoft/dcp/issues/34 is implemented), and logs. We could then build an AI chat experience on top of that.

Specific things to investigate (in no particular order):

- [ ] Make DCP an MCP server
- [ ] Build a CLI chat experience for diagnosing app execution, using DCP as a source of data (model, model history, logs)
- [ ] Make DCP an OTEL sink and add enhance MCP implementation to serve metrics, traces, and structured logs
- [ ] Hack Aspire dashboard to separate OTEL store from the rest of the dashboard and replat the dashboard on top of DCP OTEL store.

Contributor guide

Open the 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.

Research direction

Start by reading the linked Model Context Protocol architecture documentation and issue #34, then break down the checklist into the MCP server, CLI chat, OTEL sink, and dashboard work. The issue does not name files or tests; done would require defining and completing a narrower scope for exposing DCP models, history, logs, metrics, or traces.

Written by the indexing model from the issue text.

Assessment

Tech stack
go
Domain
backend, cli, observability
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.