Skip to content

docs: Partner MCP proof surface + architecture note #105

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
d3v07 merged 1 commit into from
Jun 8, 2026
Merged

docs: Partner MCP proof surface + architecture note #105

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,22 @@ DBRE ─ login ─> Slow-Query Queue (ranked by evidence)

The dashboard reads only `EvidencePack` v1 JSON; that contract is frozen in `contracts/`.

## Partner integration — MongoDB via MCP

The agent reads MongoDB through MongoDB's official **MCP server** (`mongodb-mcp-server`). Prove it
live in one command — it spawns the MCP server, runs the MCP handshake, calls the `explain` tool
against Atlas, and prints the HIGH finding + ESR recommendation derived from the real plan:

```bash
uv run --with python-dotenv python -m agents.run
```

The MCP wiring lives in `agents/agent.py` (`build_mcp_toolset`, ADK `MCPToolset`) and
`agents/run.py` (raw stdio JSON-RPC). In the managed Vertex AI Agent Engine runtime the same
read-only operations run as native Python tools (`agents/native_mongo_tools.py`), because MCP's
stdio transport can't run inside that sandbox — so the MCP integration is demonstrated locally /
controller-side and the production agent uses the native equivalents.

## Quickstart

```bash
Expand Down
Loading