micro APImicro.mu ↗
Browse all 33 micro.mu services and ~120 methods, or fetch full argument details for any tool. Covers MCP server config, service listings, and per-tool specs.
What is the micro API?
The micro.mu Tools API exposes 3 endpoints for reading the micro.mu service catalogue, which spans 33 services and roughly 120 methods. The list_tools endpoint returns every service grouped with its methods, descriptions, and cost info, while get_tool retrieves the full argument schema for any individual tool by its snake_case name. A third endpoint, get_mcp_server_info, returns the MCP server configuration needed to register micro.mu in any MCP-compatible client.
curl -X GET 'https://api.parse.bot/scraper/2963bf56-88ac-44ad-b5bc-3f10192cb37d/list_tools?service=weather' \ -H 'X-API-Key: $PARSE_API_KEY'
List all available tools from the micro.mu catalogue, grouped by service. Each service contains its methods with descriptions, API paths, auth requirements, and cost info. Optionally filter by service name to see only one service's tools. Returns all 33 services and ~120 methods when unfiltered.
| Param | Type | Description |
|---|---|---|
| service | string | Filter by service name (e.g. 'weather', 'news', 'flights'). When omitted, all services are returned. |
{
"type": "object",
"fields": {
"services": "array of service objects, each with service name, description, scoped flag, and methods array",
"total_services": "integer count of services returned"
},
"sample": {
"data": {
"services": [
{
"scoped": false,
"methods": [
{
"cost": null,
"name": "weather_air",
"path": "/api/v1/weather/air",
"method": "Air",
"needs_auth": false,
"description": "Air quality at a location right now",
"destructive": false
},
{
"cost": "weather_forecast",
"name": "weather_forecast",
"path": "/api/v1/weather/forecast",
"method": "Forecast",
"needs_auth": false,
"description": "Get the weather forecast for a location",
"destructive": false
}
],
"service": "weather",
"description": "Forecast, air quality, sea state and what the weather actually was"
}
],
"total_services": 1
},
"status": "success"
}
}About the micro API
What the API covers
The API gives read access to the public micro.mu tools catalogue. list_tools returns an array of service objects — each containing the service name, description, a scoped flag, and an array of method objects with API paths, auth requirements, and cost info. An optional service parameter (e.g. weather, news, flights) limits the response to a single service, keeping payloads small when you only care about one domain.
Per-tool detail
get_tool accepts a required name parameter in snake_case format — for example apps_read, weather_forecast, or news_search — and returns the full schema for that method: its title, service, description, an arguments array where every entry carries name, type, description, and a required flag, plus read_only and idempotent booleans. This is the right endpoint when you need to validate inputs before calling a tool or when building a UI that renders forms from schema.
MCP server configuration
get_mcp_server_info requires no inputs and returns the fields needed to register micro.mu as an MCP server: server_name, server_version, protocol_version, transport (e.g. streamable-http), auth_method (e.g. bearer_token), auth_env_var, capabilities, and total_tools. This is useful for automated toolchain setup where MCP client configuration must be generated programmatically.
Coverage notes
All three endpoints are read-only. The catalogue data — service count, method count, and argument schemas — reflects the micro.mu tools page at time of request. No write operations against micro.mu services are exposed through this API.
The micro API is a managed, monitored endpoint for micro.mu — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when micro.mu changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official micro.mu API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Building an MCP client configurator that reads server metadata from
get_mcp_server_infoand auto-generates connection config. - Generating a browsable documentation site from the full service and method list returned by
list_tools. - Validating tool call payloads by checking required arguments returned by
get_toolbefore forwarding a request. - Populating a tool-picker UI that groups methods by service using the
servicesarray fromlist_tools. - Auditing which micro.mu tools are marked
read_onlyvs. stateful by iterating theread_onlyfield across all tools. - Discovering all services that require auth by scanning the auth requirements in the
methodsarray fromlist_tools. - Automatically syncing a local tool registry by comparing
total_toolsfromget_mcp_server_infoagainst a cached snapshot.
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 200 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
| Team | $300/mo | 20,000 | 300 req/min |
| Company | $1,000/mo | 100,000 | 500 req/min |
Each endpoint has a fixed posted price per successful call — most fall between 1 and 10 credits — shown on this API's page before you run it. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does micro.mu provide an official developer API?+
How does filtering work in `list_tools`, and what does the response include when a service filter is applied?+
service string parameter — for example weather or flights — to list_tools. The response narrows to a single entry in the services array, and total_services reflects the count of matched services (typically 1). Without the filter, all 33 services and their methods are returned.Does the API expose the actual output schemas for tool responses, not just input arguments?+
get_tool returns input arguments with name, type, description, and required flag, plus read_only and idempotent booleans and a text description. Output field schemas are not included. You can fork this API on Parse and revise it to add an endpoint that surfaces output schemas if micro.mu exposes them.Can I retrieve historical changes to the catalogue, such as which tools were added or removed over time?+
What does the `scoped` flag on a service object mean?+
scoped boolean on each service in the list_tools response indicates whether the service's methods require a scoped authorization context. When true, consuming those methods typically requires credentials or a token scoped to that service rather than a generic API key.