atmospore
Atmospore ships BOTH a hosted remote MCP server and an open-source local stdio server. The remote endpoint at https://mcp.atmospore.com/mcp is live and answers JSON-RPC, gated by the same Atmospore API key used for REST. The local server is MIT-licensed Python published from the atmospore GitHub organization.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
get_pollen— Get the daily pollen forecast for a specific point on Earth. Returns a list of daily forecasts; each day includes date, overall_risk (Low|Moderate|High|Very High) and per-species values in grains/m3 with individual risk levels.get_top_species— Get the top contributing pollen species at a point, ranked highest first. Each entry has species slug, display_name, max_value in grains/m3, risk_level and category.get_area_average— Get tree, grass and weed pollen aggregates over a radius around a point. One entry per day with overall_risk and per-category aggregates (tree_tot, grass_tot, weed_tot).list_supported_species— List all pollen species the model tracks with slug, display name, category (tree/grass/weed), localised names (en, no, sv) and risk-level concentration thresholds.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.