MCP servers for weather, maps, travel, health, fitness and everyday local services. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
The in-deployment MCP server for the Voyant framework (voyant#2792). It exposes the framework tool registry as a real [Model Context Protocol](https://modelcontextprotocol.io) server, mounted as a Hono route group inside the operator deployment at `/v1/ad
MCP server giving AI assistants 17 weather tools with zero API keys: global forecasts, current conditions, alerts, air quality, marine conditions, lightning detection, radar imagery, river levels, wildfire tracking, and historical weather back to 1940. Bu
Thin MCP server + CLI that proxy the atrium /api/v1 observability surface using an oc_live_ Bearer key. Talks HTTP only — no Convex imports.
MCP server giving AI assistants live, sourced access to Brazilian public data — geography, census, economy and health — from the official IBGE APIs. Exact figures with provenance, not approximations.
MCP server for converting Markdown to interactive mind maps with export support (PNG/JPG/SVG)
Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, and FHIRPath filtering.
Expose any wasmagent agent as a Model Context Protocol (MCP) server — sync tools/call + 2025-11-25 Tasks for long-running agent work
OpenTelemetry instrumentation for Model Context Protocol (MCP) with distributed tracing support
Model Context Protocol (MCP) server integration for @ttoss/http-server
Model Context Protocol server for Open-Meteo weather APIs
Build MCP servers — and MCP Apps (interactive `ui://` widgets, SEP-1865) — for a nifra app. The transport-agnostic JSON-RPC core (also used by `@nifrajs/cli`'s dev MCP), a Streamable-HTTP handler you mount at `POST /mcp`, and `defineMcpWidget`/`defineMcpT
Lighthouse for MCP servers — grade any public Model Context Protocol server against 10 spec-bound readiness criteria (handshake, tool quality, safety annotations, anti-ghost content, token efficiency, honest errors) + a Claude/ChatGPT directory pre-flight
AirTreks MCP Server — complex flight routing intelligence for AI agents. Plan multi-city trips, validate alliance routings, get carrier recommendations, and create trip ideas.
MCP server for simap.ch - Swiss public procurement platform
Countersign as MCP tools — the cross-vendor kill switch + spend guard inside any MCP client (Claude, Cursor, …).
Betaflight MCP server, live CLI configuration, and an expert PID tuning assistant — powered by the MSP binary protocol and Betaflight CLI over USB serial.
MCP server for Australian address search and validation via Addressr
MCP server for querying and validating OpenStreetMap tags
Model Context Protocol server for Google Maps Platform APIs - provides geocoding, places search, routing, and geospatial tools
UniFi semantic analysis MCP server — fleet health, anomaly detection, cross-site analytics on top of Cloud API
MCP server providing access to the Flightradar24 API for real-time and historical flight data
MCP server for OOREP homeopathic repertory and materia medica - enables AI assistants to search symptoms, remedies, and homeopathic reference materials
MCP server for Polish property prices from notarial deeds, not listings - 8M+ transactions from the RCN registry
MCP server for AI-driven fair meeting point discovery
An hourly forecast, a transit timetable, a geocoded address, last night's sleep score — everyday context like this sits behind weather APIs, mapping and navigation platforms, travel and flight data, fitness trackers and local business directories. A lifestyle MCP server turns one of those services into tools the Model Context Protocol exposes to Claude, Cursor and other clients, so the assistant fetches a forecast or a route itself, no pasted-in data needed.
These pair naturally with AI, Memory & Reasoning servers that remember preferences between sessions, and with Web, Search & Scraping servers when research goes beyond structured APIs.
Security stakes in this category are personal rather than corporate. Location queries reveal a home address, a daily routine, and the dates a house sits empty; health and fitness records are among the most sensitive data an assistant ever touches. A malicious or over-permissioned MCP server here carries an outsized blast radius: a tool that should only call one weather endpoint but also holds filesystem or shell capability can move that context anywhere, and place descriptions or reviews are untrusted text that can carry prompt injection into the model. Every listing in the MCP Trust Registry has a Trust Score: the open-source engine reads the published npm or PyPI package, maps declared capabilities into a blast-radius profile, and grades it A–F deterministically — same code, same score, no AI involved, no paid rankings. The free scan API runs the same check on any package.
It can be, when a server's permissions match its job: a weather or maps tool needs network access to one API and nothing else. Check the Trust Score and capability profile before installing, and treat filesystem, shell or broad network access in a lifestyle tool as a red flag. Scores are automated opinions about published code, not certifications, so stick to well-scored, actively maintained MCP servers for health and location data.