Provides tools for managing day-by-day travel itineraries stored in SQLite, including adding activities with guard rails, removing activities, and retrieving full itineraries grouped by day.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Trip Planner Plan a 3-day trip to Kyoto, Japan"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Local Scout ──▶ tavily-mcp can search the web, cannot touch the trip
Planner ──▶ itinerary_server can write the trip, has no internetThe 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.
Related MCP server: wanderlog-mcp
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 3That check is in db.py, not in the instructions. The agent gets a
real error back and has to correct itself — which it does.
uv sync
cp .env.example .env # add your keysTwo 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.
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 itineraryPoint it at a different model with one env var:
PLANNER_MODEL=gpt-4o-miniTwo 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 CristalDay 1 is the historic centre, Day 2 is Gaia and the west side — grouped so a day doesn't zig-zag across the city.
Tool | What it does |
| The trip, its days, and every activity grouped by day |
| Adds one activity — rejects out-of-range days |
| 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.
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 CLIFour files, about 330 lines.
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.
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.
Add one activity to a specific day of the trip. day must be between 1
and the trip's length. Put the practical notes in details: why it's worth
doing, roughly how long it takes, and anything to book ahead.
| Name | Required | Description | Default |
|---|---|---|---|
| day | Yes | ||
| title | Yes | ||
| details | No | ||
| trip_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context about the day range ('must be between 1 and the trip's length') and the purpose of the details field, but it does not mention error handling, side effects, idempotency, or what the response contains. This is partial transparency, not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action and target, followed by essential parameter guidance. Every sentence adds value without redundancy, making it concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple add operation with four parameters and an existing output schema, the description covers the core purpose, the key day validation rule, and the details field's intended use. It doesn't address potential errors or return behavior, but these are partially covered by the output schema and the simplicity of the tool. Overall, it is sufficient but not exhaustive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It meaningfully explains the 'day' parameter (range constraint) and 'details' (content guidance), adding value beyond the plain schema titles. The other parameters (trip_id, title) are self-explanatory and not explicitly described, but the description still covers the non-obvious ones.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb and resource: 'Add one activity to a specific day of the trip.' This is specific and distinguishes the tool from siblings get_itinerary (retrieval) and remove_activity (deletion), which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by stating the action and location ('to a specific day of the trip') and provides constraints on the day parameter. However, it does not explicitly name alternatives or state when not to use this tool, leaving differentiation to inference from the verb and sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read the current itinerary for a trip: the place, how many days, and every activity already planned, grouped by day. Call this first.
| Name | Required | Description | Default |
|---|---|---|---|
| trip_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of disclosing behavior. The explicit 'Read' verb signals a non-mutating operation, and the description clearly states what content is returned. It lacks mention of edge cases or prerequisites, but for a simple read tool this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two short sentences, front-loaded with the core action and immediately followed by a concise summary of what is returned. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter read tool with an output schema, the description covers the essential usage ('Call this first') and return contents. No further detail is needed given the tool's simplicity and available structured data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has a single parameter (trip_id) with 0% description coverage, and the description only implies a trip context without explicitly naming or explaining the parameter. Since schema coverage is low, the description should have compensated by mentioning trip_id or its role, but it does not.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads the current itinerary for a trip and details its contents (place, days, activities grouped by day). The verb 'read' and resource 'itinerary' distinguish it from sibling mutation tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The instruction 'Call this first' provides explicit usage context, positioning this read tool as a preliminary step before modifications. However, it does not explicitly mention when not to use it or name alternatives, so it stops short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Remove an activity by its id. Ids are shown in square brackets by get_itinerary.
| Name | Required | Description | Default |
|---|---|---|---|
| activity_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the full burden of behavioral disclosure. It fails to mention whether the removal is permanent, whether special permissions are required, or what happens if the id does not exist. The only extra behavior is the pointer to get_itinerary for finding ids, which is more about parameter retrieval than tool behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences: the first clearly states the action, and the second adds a useful pointer. No superfluous words or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the presence of an output schema, and the description covering the core action and id provenance, the description is largely complete. It omits mention of permanence or error handling, but these are not critical given the straightforward nature of the operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema coverage, the description adds significant meaning to the activity_id parameter by explaining that ids are shown in square brackets by get_itinerary. This directly tells the agent where to obtain a valid value, compensating for the missing schema description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Remove') and resource ('activity') and an explicit method ('by its id'). It distinguishes from siblings by indicating removal versus get_itinerary (listing) and add_activity (creation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear workflow context by telling the agent that ids are found in square brackets via get_itinerary. This implies the prerequisite action and when to use this tool, though it does not explicitly name alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0add_activityget_itineraryremove_activityScored across 3 tools
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.
All tool names follow the same verb_noun pattern with snake_case: get_itinerary, add_activity, remove_activity. This is fully consistent and predictable.
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.
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.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Corporate travel booking and expense management for TripGain, exposed as an MCP server.
Flight search MCP server providing search, pagination, and itinerary details for AI assistants.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
