The request names FHIR, a healthcare data standard, so no product is a direct FHIR toolkit by name. FHIRfly 1 is the only candidate that explicitly enriches FHIR codes with human-readable meaning via API, SDK, or MCP, and the 'fhir-developer-skill' action in Anthropic's listing 2 is a FHIR API development guide for building healthcare endpoints. Other candidates (Docker, Supabase, Snowflake, Firecrawl, Figma, GitHub, Browserbase, MCP SDK) do not show FHIR-specific capability in their sources
- 1
FHIRflyfhirfly.iowebsite read, tools not yet checked
Adds human-readable meaning to FHIR codes (provider, drug, lab, specialty names, ICD-10 descriptions) via API, SDK, or MCP server, with no sign-up required.
official:MCP server · io.fhirfly/mcp-server
- 2
Anthropicanthropic.comverified and signed
Its indexed fhir-developer-skill action is a FHIR API development guide for building healthcare endpoints such as Patient and Observation REST resources.
+71 community tools built for it
for agents: fhir-developer-skill · skill-development · skill-development
Sources
- 1Healthcare terminology, enriched NPI, NDC, ICD-10 & more | FHIRflyfhirfly.io · read 2026-10-29
- 2Home \ Anthropicanthropic.com · read 2026-10-29
For agents: the 10 actions behind this answer
· FHIRfly website read, tools not yet checked
Raw FHIR gives you a code; FHIRfly gives you the meaning. Provider, drug, lab, and specialty names across 21+ healthcare data types via API, SDK, or MCP. Free tools, no sign-up.
fhir-developer-skill · fhir-developer-skill verified and signed
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authoriza
docker-project-foundations · docker-project-foundations verified and signed
Use this skill when setting up, initializing, or Dockerizing a project, even if the user doesn't explicitly mention Docker but describes a need for containerized local development, adding a database or cache dependency, or running services without host-level installs. Covers Dockerfile, compose.yaml
skill-creator · skill-creator verified and signed
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
mcp-apps · mcp-apps verified and signed
Skills for creating MCP Apps with the MCP Apps SDK
snowflake-cortex-code · snowflake-cortex-code verified and signed
Automatically route Snowflake prompts from Claude Code to Cortex Code for execution. Provides slash commands for code review and task delegation, plus skills for routing, run, and setup.
firecrawl-build-onboarding · firecrawl-build-onboarding verified and signed
Get Firecrawl credentials and SDK setup into a project. Use when an application needs `FIRECRAWL_API_KEY`, when an agent should add Firecrawl to `.env`, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill inc
figma-design-to-code · figma-design-to-code verified and signed
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool. You MUST trigger this skill whenever the user wants to implement, build, port, or code up a Figma design as code. Example prompts (not exhaustive) are 'implement this Figma design', 'build
minecraft-plugin-development · minecraft-plugin-development verified and signed
Use this skill when building or modifying Minecraft server plugins for Paper, Spigot, or Bukkit, including plugin.yml setup, commands, listeners, schedulers, player state, team or arena systems, persistent progression, economy or profile data, configuration files, Adventure text, and version-safe AP
agent-experience · agent-experience verified and signed
Audit the developer experience of a product, SDK, docs site, or SKILL.md by dropping multiple Claude subagents at it with only a tiny task prompt and real tools (WebFetch, Bash, Write). Agents must discover the docs themselves, install deps, ask for credentials if needed, and attempt real execution.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.