Allows comparing door-to-door travel times by bicycle, motorbike, and public transport using the Google Maps Routes API, and returns weather at departure.
Provides address search and disambiguation using the French Base Adresse Nationale (IGN) geocoding service.
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., "@route-mcp Compare bike, motorbike, and transit times from Paris to Versailles, plus weather."
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.
MCP server comparing door-to-door travel time in Île-de-France by bicycle, motorbike (estimate) and public transport, with local weather, plus a terminal chat client driven by a local LLM (Ollama).
Design decisions and their rationale: docs/TECHNICAL_REPORT.md.
Tool | What it does | Metered? |
| Travel time per mode between two places, fastest mode, weather at departure | Google Routes: 1 Essentials call each for bicycle and transit, 1 Pro call for motorbike |
| Current conditions + hourly forecast (up to 48 h) | Open-Meteo (free, daily cap) |
| Disambiguate an address or place name | Free |
| Calls used / remaining per budget | Free |
Related MCP server: Singapore Location Intelligence MCP
Python 3.12+
Ollama with llama3.1:8b pulled (client only)
A Google Maps Platform API key with the Routes API enabled (routes only; weather and geocoding need no key)
python3 -m venv .venv
.venv/bin/pip install -e ".[client,dev]"
cp .env.example .env # then set ROUTE_MCP_GOOGLE_MAPS_API_KEYBefore using a real key, apply the Google Cloud Console safeguards described in the report (API restriction + daily quota).
Then check the key with one real request (counted in the usage ledger):
.venv/bin/route-mcp-check-google # bicycle, Routes Essentials
.venv/bin/route-mcp-check-google --mode motorbike # also checks the Routes Pro SKUOn failure it prints Google's error reason (API not enabled, key restriction, billing...) and how to fix it.
# Terminal chat (starts the MCP server itself over stdio)
.venv/bin/route-mcp-chat
# commands: /tools /usage /viewer /reset /help /quit
# trace viewer: open http://127.0.0.1:8765 while chatting
# Server alone, for any MCP host (Claude Desktop, MCP Inspector, ...)
.venv/bin/route-mcp-serverExample MCP host configuration:
{
"mcpServers": {
"route-mcp": {
"command": "/absolute/path/to/route-MCP/.venv/bin/route-mcp-server",
"env": { "ROUTE_MCP_GOOGLE_MAPS_API_KEY": "..." }
}
}
}android/: native Android app (Kotlin, Jetpack Compose). Saved places and the API
token stay on the phone. Built so a home-screen widget can reuse the same data layer.
route-mcp-api: the HTTP API the app calls, meant for a server (Docker + Caddy for HTTPS). Deployment
guide: docs/DEPLOY_VPS.md.
POST /v1/advice: comparison and rule-based choice, from coordinates sent by the phone.
POST /v1/advice/{id}/explanation: two or three sentences by Claude Opus 5 (server-side refusal
fallback enabled), written once per advice and capped per day in the usage ledger.
GET /v1/places/search, GET /v1/usage, and GET /v1/health (the only route without a token).
Every other route requires Authorization: Bearer $ROUTE_MCP_API_TOKEN.
A local web page to save four places (home, pool, athletics track, work), get your position from the browser, and get advice on the best mode to reach one of them.
.venv/bin/pip install -e ".[app,dev]"
.venv/bin/route-mcp-app # then open http://127.0.0.1:8766Places are searched with find_place (free) or set from your current position, and saved in
~/.route-mcp/places.json (owner-only permissions).
Advice calls compare_routes through the MCP server over stdio, from your position to the place.
The mode is chosen by fixed rules, not by the model: travel time, plus penalties for rain, strong gusts and cold on two wheels, a warm-up bonus for cycling to the track, and a penalty for a bike ride over 25 minutes to work. The rules are listed on screen with the result.
The local model (Ollama) then writes a two- or three-sentence explanation. If it is unavailable, the rule-based reasons are shown on their own.
Cost per advice: at most 2 Routes Essentials calls and 1 Routes Pro call, reused for 5 minutes.
The browser only shares your position on localhost or HTTPS, so the page must be opened on this machine.
The chat serves a local debugging page at http://127.0.0.1:8765 (standard library only, bound to
localhost). It updates live and shows, for each question:
every LLM round: latency, prompt/output tokens against the context window, thinking text (for models that emit it), the tool calls requested, and the exact prompt sent (after history trimming);
every tool call: arguments, latency, the result as fed back to the model, and errors;
the final answer, a forced answer when the tool-round limit is hit, or the exception.
The last 50 questions are kept in memory. Change the port or disable it with ROUTE_MCP_CLIENT_VIEWER_PORT
(0 = off).
.venv/bin/pytest # offline: every upstream API is faked
.venv/bin/ruff check src testsAll settings are environment variables (or .env), listed with their defaults in .env.example.
The usage ledger lives in ~/.route-mcp/usage.sqlite3: keep one per API key.
Routes: Google Maps Platform Routes API (Google terms apply).
Geocoding: Géoplateforme / Base Adresse Nationale (IGN), free service.
Weather: Open-Meteo, CC BY 4.0. The free API is for non-commercial use only.
Compare door-to-door travel time by bicycle, motorbike and public transport (metro, RER, bus, tram) between two places in Île-de-France. Motorbike times are estimates.
| Name | Required | Description | Default |
|---|---|---|---|
| modes | No | Subset of bicycle, motorbike, transit. Omit to compare all. | |
| origin | Yes | Start: address, place name, or 'lat,lon' | |
| destination | Yes | End: address, place name, or 'lat,lon' | |
| departure_time | No | Local departure time, ISO 8601 (e.g. 2026-09-15T08:30). Omit to leave now. | |
| include_weather | No | Add the weather at the origin at departure |
| Name | Required | Description |
|---|---|---|
| notes | No | |
| origin | Yes | |
| results | Yes | |
| destination | Yes | |
| fastest_mode | Yes | |
| departure_time | Yes | Local time, ISO 8601 |
| weather_at_departure | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds a useful behavioral caveat ('Motorbike times are estimates') and geographic scope, but does not disclose details like data freshness, response format, or how transit modes are computed. This is adequate but not rich.
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?
Two tight sentences deliver the core purpose, the mode list, the geographic scope, and the key caveat with no filler. The most important information is front-loaded.
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 rich input schema, the output schema, and annotations, the description covers the essential behavioral context. Nothing critical is missing for an agent to understand what the tool does and how to invoke it correctly.
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 100%, so all parameters are already documented with meaningful descriptions. The tool description introduces the set of modes referenced by the modes parameter but adds no new semantics beyond what the schema provides.
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 a specific action ('Compare door-to-door travel time') on a specific resource (travel between two places in Île-de-France) and enumerates the comparison modes. It is immediately distinct from sibling tools like get_weather or find_place.
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 conveys a clear use case: comparing door-to-door travel times across specific modes within a geographic scope. It does not explicitly name alternatives or exclusions, but the context is strong enough that an agent can infer when to use this tool versus the siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the best matching places in Île-de-France for an address or name. Use it when a place is ambiguous, before comparing routes.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Address or place name |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description only needs to add extra behavioral context. It adds geographic scope and 'best matching' ranking, but does not explain result limits, no-match behavior, or ambiguity resolution details beyond what the schema and output schema likely provide.
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?
Two short sentences front-load the core purpose and immediately add the critical usage context. No redundant or filler content is present.
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 single-parameter, read-only tool with an output schema and strong annotations, the description covers what the tool does, where it applies, and how it relates to sibling tools. Nothing essential is missing for an agent to invoke it correctly.
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 100%, with the query parameter already described as 'Address or place name.' The description echoes this without adding substantial new meaning, so a baseline score of 3 is appropriate.
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 states a specific action ('List the best matching places') on a specific resource (places in Île-de-France) for an address or name. It clearly differentiates the tool from siblings like compare_routes by focusing on disambiguation rather than routing.
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 explicitly says 'Use it when a place is ambiguous, before comparing routes,' giving both a clear condition for use and an ordering alongside the compare_routes sibling. This tells an agent when to invoke this tool versus a likely alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How many metered API calls are used and remaining in the current period, per budget.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the agent knows it's a safe, read-only operation. The description adds the 'per budget' detail, which is useful context beyond annotations. However, it doesn't disclose what happens if there is no budget or how often the data refreshes, which could affect interpretation. No contradiction with annotations.
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 a single, focused sentence that front-loads the core purpose. Every word earns its place; it conveys the what, the metric (metered calls), the state (used/remaining), the timeframe (current period), and the granularity (per budget) without redundancy.
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?
The tool is simple (no parameters, no nested objects) and has an output schema, so the description doesn't need to detail return values. It covers the essential aspects an agent needs to call it correctly – what it returns and how it's organized. It could mention what happens if no budget is set, but that's a minor gap given the simplicity.
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 tool has zero parameters, and schema coverage is 100% (vacuously). The description explains the tool's output context (usage and remaining per budget), which is sufficient given no parameters need documentation. Since there are no parameters to explain, the description's mention of time period and budget adds value over the empty schema.
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 reports metered API call usage and remaining quota per budget. It identifies a specific resource (API usage) and informative detail (used/remaining, current period, per budget), which distinguishes it from siblings like get_weather or compare_routes. However, it doesn't explicitly name a sibling it differentiates from, and the title 'API usage' is somewhat generic.
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 the tool is for checking API consumption quotas, which is clear enough for an agent to know when to use it. However, it doesn't explicitly state when not to use it or mention alternatives (e.g., if you need detailed logs or per-endpoint breakdowns). The sibling list doesn't help since they are unrelated to usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current weather and hourly forecast (temperature, rain, wind) for a place in Île-de-France.
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | Number of hourly forecasts to return | |
| location | Yes | Address, place name, or 'lat,lon' | |
| start_time | No | Local start of the forecast, ISO 8601. Omit for now. |
| Name | Required | Description |
|---|---|---|
| place | No | |
| hourly | Yes | |
| current | Yes | |
| timezone | Yes | |
| attribution | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds behavioral context beyond annotations: it specifies the data returned (temperature, rain, wind) and the geographical restriction (Île-de-France). It does not contradict annotations and provides useful operational detail.
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 a single, efficient sentence that front-loads the core purpose (current weather and hourly forecast) and includes key data types and scope. There is no wasted wording or redundant information.
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 moderate complexity (3 params, 1 required), an existing output schema, and annotations covering safety, the description is sufficiently complete. It states what data is returned and the geographical scope. It does not mention units or timezone, but the schema covers start_time format and the output schema likely defines return structure, so nothing critical is missing.
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 input schema has 100% description coverage for all three parameters, so the schema already documents location, hours, and start_time. The tool description does not add any parameter-specific meaning beyond what the schema provides; it only mentions 'a place' which maps to location. Baseline 3 is appropriate since the schema does the heavy lifting.
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 returns current weather and an hourly forecast with specific data (temperature, rain, wind) for a place in Île-de-France. It distinguishes itself from sibling tools like compare_routes (routes), find_place (place lookup), and get_api_usage (API usage) by resource and scope. The verb is implied by the tool name but the description is specific about what it provides.
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 context: it is for weather in Île-de-France. While it does not explicitly name alternatives or exclusions, the sibling tools are clearly different domains, so an agent can infer when to use this tool. There is no contradictory guidance, and the scope is explicit.
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.
v0.1.0compare_routesfind_placeget_api_usageget_weatherScored across 4 tools
Each tool has a clearly distinct purpose: place lookup, route comparison, weather lookup, and API usage monitoring. There is no meaningful overlap between any of the tools.
All tools follow a consistent verb_noun pattern: compare_routes, get_weather, find_place, get_api_usage. The naming convention is uniform and predictable.
Four tools is a reasonable, focused scope for a routing assistance server. Each tool serves a necessary function and none feel redundant or excessive.
The core workflow is covered: find a place, compare routes, and optionally check weather. Minor gaps exist such as lack of route detail endpoints or alternative route options, but the essential use case is well supported.
Find and rank 100 audited APIs for weather, geospatial, IoT, robotics, mobility and logistics.
Geocoding, weather forecasts, and timezone lookups
Weather data, forecast API, climate data, historical weather, alerts, agricultural & travel weather.
Weather, climate, terrain, fire and flood risk data for any point or polygon on Earth. Free tier.
