Skip to main content
Glama
Nirmai3799
by Nirmai3799
README.md
# Trip Planner — two agents, one enforced boundary

A trip planner built on the **Model Context Protocol**. You name a place and a
number of days; a planner agent researches it and builds a real day-by-day
itinerary in SQLite.

The interesting part isn't that it plans trips. It's **how the two agents are
kept apart**.

## The boundary

```
Local Scout  ──▶  tavily-mcp          can search the web, cannot touch the trip
Planner      ──▶  itinerary_server    can write the trip, has no internet
```

The Planner has no search tool. Its *only* route to the outside world is calling
`research_place` — which is the Scout, attached to it as an ordinary tool via
`.as_tool()`. The Scout, in turn, has no itinerary tools, so it structurally
cannot write to the trip no matter what it decides to do.

Neither restriction is a prompt. Each agent is handed a different set of MCP
servers, and that's the whole enforcement mechanism. Prompts can be talked
around; a tool that isn't in the list cannot be called.

## Guard rails live in the server

`add_activity` rejects a day outside the trip's length:

```
> add_activity(trip_id=1, day=99, title="...")
Rejected: Day 99 is outside this 3-day trip - use a day from 1 to 3
```

That check is in [`db.py`](db.py), not in the instructions. The agent gets a
real error back and has to correct itself — which it does.

## Setup

```bash
uv sync
cp .env.example .env      # add your keys
```

Two keys are needed: `OPENAI_API_KEY` (or another provider via `PLANNER_MODEL`)
and `TAVILY_API_KEY` for the Scout's search. `npx` must be on your PATH — the
Tavily MCP server runs through it.

## Run it

```bash
uv run main.py              # create a trip, plan it, print it
uv run main.py --list       # list existing trips
uv run main.py --show 1     # re-print one itinerary
```

Point it at a different model with one env var:

```bash
PLANNER_MODEL=gpt-4o-mini
```

## What a run looks like

Two days in Porto, planned from scratch:

```
=== Trip 2: Porto, Portugal (2 days) ===

Day 1
  - São Bento Railway Station
      Iconic tiled station hall and an easy first stop in the historic centre.
      Allow 15–20 minutes. No booking needed.
  - Sé do Porto (Porto Cathedral)
      Main old-city cathedral and a strong historic anchor. Allow 30–45 minutes.
  - Ribeira
      Porto's classic riverfront old quarter. Allow 1–2 hours.
  - Palácio da Bolsa
      Ornate 19th-century interiors; one of the best paid visits in the centre.
      Book ahead for guided tours.
  - Torre dos Clérigos
      The classic bell tower and city panorama. Booking ahead helps at busy times.

Day 2
  - Dom Luís I Bridge
  - Port wine cellars in Vila Nova de Gaia
  - Jardim do Morro
  - Jardins do Palácio de Cristal
```

Day 1 is the historic centre, Day 2 is Gaia and the west side — grouped so a day
doesn't zig-zag across the city.

## The MCP server

| Tool | What it does |
| --- | --- |
| `get_itinerary(trip_id)` | The trip, its days, and every activity grouped by day |
| `add_activity(trip_id, day, title, details)` | Adds one activity — rejects out-of-range days |
| `remove_activity(activity_id)` | Removes one by id |

It speaks stdio, so the agent launches it as a subprocess. The Scout's server,
`tavily-mcp`, is filtered down to just `tavily_search` — hiding crawl, map and
extract keeps its tool list small and its behaviour predictable.

## Layout

```
db.py                 SQLite schema and access — trips, activities, guard rails
itinerary_server.py   MCP server: the only way the trip gets written
planner.py            Scout on Tavily, wrapped via .as_tool(); Planner on itinerary
main.py               CLI
```

Four files, about 330 lines.

## Notes

- The project sets `link-mode = "copy"` and passes `UV_LINK_MODE=copy` to every
  spawned MCP server, so it works on a cloud-synced drive (OneDrive, Dropbox),
  where `uv`'s default hardlinking fails with `os error 396`.
- `main.py` reconfigures stdout to UTF-8 — accented place names would otherwise
  print as mojibake in the Windows console.

## Verified

Both parts were tested for real, not assumed:

- The MCP server over stdio: tool listing, an itinerary read, and the day guard
  rail correctly rejecting `day=99` on a 3-day trip.
- A full end-to-end run on a 2-day Porto trip — the Scout searched, the Planner
  wrote nine activities, grouped geographically, with booking notes on the two
  that need them.

TDQS

A4.3/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: reading the itinerary, adding an activity, and removing an activity. There is no overlap or ambiguity between them.

Naming Consistency5/5

All tool names follow the same verb_noun pattern with snake_case: get_itinerary, add_activity, remove_activity. This is fully consistent and predictable.

Tool Count5/5

Three tools is well-scoped for a simple trip planner. Each tool earns its place, and the count is neither too thin nor excessive for the apparent purpose.

Completeness4/5

The set covers the core lifecycle of reading, adding, and removing activities. The only minor gap is the lack of an update operation, but this can be worked around with remove_activity followed by add_activity.

Maintenance

ActivitySlowing
ResponsivenessNo issues