LLM komplet | FastComments Docs

LLM Kit

FastComments LLM Kit pomaže AI asistentima za kodiranje poput Claudea, ChatGPT-a i Cursora da razumiju i integriraju FastComments pružajući im pristup našoj kompletnoj dokumentaciji putem jednostavnog pretraživačkog API-ja.

Dodavanjem isječka u AGENT.md ili CLAUDE.md datoteku vašeg projekta omogućujete AI asistentima brzo pretraživanje i dohvaćanje relevantne FastComments dokumentacije, čime je implementacija brža i točnija.

Nabavite LLM komplet

Dodajte ovaj isječak u konfiguracijske datoteke AI asistenta vašeg projekta (poput AGENT.md ili CLAUDE.md) koji uči AI asistente za kodiranje kako pretraživati i pristupiti dokumentaciji FastComments.

FastComments LLM Kit

Copy

## FastComments Integration
FastComments is an embeddable live commenting platform with libraries for many frontend and backend integrations, along with client and server-side SDKs and APIs.
When working with FastComments, you can search the FastComments documentation by calling this API:
https://docs-search.fastcomments.com/search?query=<search_query>&full=true&tenantId=demo
Replace `<search_query>` with your search terms (URL encoded). The API returns relevant documentation snippets to help with implementation.

Na ovaj način vaš AI asistent može lako dobiti ažurirane informacije i pružiti točnije implementacije u kraćem vremenu.

Primjer korištenja

Kada koristite AI asistenta poput Claude Code ili Cursor, možete postavljati pitanja poput:

"Kako instalirati FastComments na React?"
"Pokaži mi kako konfigurirati SSO s FastComments"
"Koje su opcije autentifikacije FastComments API-ja?"

AI asistent će automatski pretražiti dokumentaciju koristeći navedenu API krajnju točku i dati vam točne, ažurirane odgovore temeljene na službenoj dokumentaciji.

MCP poslužitelj

FastComments pokreće hostirani Model Context Protocol (MCP) server tako da AI pomoćnici za kodiranje i agentski klijenti mogu izravno pozivati FastComments API. Svaki alat koji MCP server izlaže automatski je generiran iz javne OpenAPI specifikacije, pa sve što REST API može učiniti, MCP klijent također može učiniti.

The endpoint is stateless and streamable-HTTP based. There's no session to keep alive, no client registration step, and no server-side state per client.

Endpoint

MCP krajnja točka

Copy

https://fastcomments.com/mcp?tenantId=YOUR_TENANT_ID&API_KEY=YOUR_API_KEY

Authentication uses the same API key as the REST API. You can also pass tenantId and the key as x-tenant-id and x-api-key HTTP headers if your client supports custom headers.

Unaprijed konfigurirano postavljanje

The dashboard has a setup helper that generates the URL and ready-to-paste config snippets for popular MCP clients. Go to your account dashboard and open Integrate -> MCP Server, or visit it directly:

Stranica za postavljanje

Copy

https://fastcomments.com/auth/my-account/mcp-setup

Pick which API key to use from the dropdown, then copy any of the generated snippets.

Claude Code

Postavljanje Claude Code

Copy

claude mcp add --transport http fastcomments 'https://fastcomments.com/mcp?tenantId=YOUR_TENANT_ID&API_KEY=YOUR_API_KEY'

After it's registered, run /mcp inside a Claude Code session to confirm the connection and list available tools.

Claude Desktop / Cursor

Add this block to your client's MCP servers config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor):

Konfiguracija MCP klijenta

Copy

{
  "mcpServers": {
    "fastcomments": {
      "type": "http",
      "url": "https://fastcomments.com/mcp?tenantId=YOUR_TENANT_ID&API_KEY=YOUR_API_KEY"
    }
  }
}

Sigurnost

The API key is embedded in the URL. Treat the URL like a secret: do not paste it into public chats, screenshots, or commits. If a key is exposed, rotate it on the API Keys page in your dashboard.

Jezik 🇭🇷 Hrvatski

Integracija LLM-a

MCP poslužitelj

LLM Kit

Nabavite LLM komplet

Primjer korištenja

MCP poslužitelj

Endpoint

Unaprijed konfigurirano postavljanje

Claude Code

Claude Desktop / Cursor

Sigurnost