Wire Fiber AI into Claude Code, Cursor, Codex, OpenCode, and 40+ other agents — plugins, MCP servers, and skills that search and enrich for you.

Developing with AI Agents

You don't have to choose between "using the dashboard" and "writing code." Fiber AI ships first-class agent integrations, so your AI assistant can search companies, reveal contacts, and build audiences for you — inside the editor you already use.

Method	Best for
Plugins (Claude Code, Cursor)	Fastest setup — MCP servers, skills, and agent rules in one install
MCP servers	Any MCP-compatible assistant — see MCP for AI agents
Skills	Teaching any of 40+ agents how to call Fiber APIs correctly
SDKs (TypeScript, Python)	Applications and pipelines — see SDKs
Context7	Live SDK documentation inside your agent while it writes code

Prerequisites

Get an API key at fiber.ai/app/api (starts with sk_live_), then export it:
```
export FIBERAI_API_KEY=sk_live_...
```
Add it to your shell profile so it persists.
Have credits. Most operations consume credits — check your balance at fiber.ai/app/subscription and see Billing & credits.

Plugins (recommended)

One install gives you two MCP servers (V2 direct tools + Core meta-tools), seven skills (search, enrich, audience, sdk-ts, sdk-py, setup, help), agent rules for credit-aware workflows, and session hooks that remind you to set your API key.

Claude Code:

claude plugin marketplace add fiber-ai/fiber-ai-plugin --scope project
claude plugin install fiber --scope project

Then run /fiber:help to see everything:

Command	What it does
`/fiber:search "AI companies in NYC"`	Search companies or people matching criteria
`/fiber:enrich "linkedin.com/in/x"`	Reveal email/phone for a person or company
`/fiber:audience "Series A fintechs"`	Build a prospecting list with bulk enrichment and export
`/fiber:sdk-ts` / `/fiber:sdk-py`	Help writing SDK code in TS or Python
`/fiber:setup`	Configure your API key and verify connection

Cursor: install Fiber AI from the Cursor marketplace (Settings → Plugins), or use the MCP deeplinks on the MCP page.

Commit an MCP config so the whole team gets Fiber automatically — no individual setup:

{
  "mcpServers": {
    "fiber-ai-v2": { "type": "http", "url": "https://mcp.fiber.ai/mcp/v2" },
    "fiber-ai-core": { "type": "http", "url": "https://mcp.fiber.ai/mcp" }
  }
}

Use .mcp.json at project root for Claude Code, .cursor/mcp.json for Cursor, .vscode/mcp.json for VS Code. Reference your key via headers ("x-api-key": "${env:FIBERAI_API_KEY}") rather than committing it.

Individual MCP setup

If no plugin exists for your editor, add the MCP servers by hand — full per-editor instructions live on MCP for AI agents:

# Claude Code
claude mcp add --transport http fiber-ai-v2 https://mcp.fiber.ai/mcp/v2
claude mcp add --transport http fiber-ai-core https://mcp.fiber.ai/mcp

# Codex
codex mcp add fiber-ai-v2 --url https://mcp.fiber.ai/mcp/v2
codex mcp add fiber-ai-core --url https://mcp.fiber.ai/mcp

OpenCode and VS Code use the same URLs in opencode.json / .vscode/mcp.json — copy the exact shapes from the MCP page.

Skills

Skills work with any agent that supports skills.sh — Claude Code, Cursor, Windsurf, Cline, and 40+ others:

npx skills add fiber-ai/fiber-ai-plugin --skill search
npx skills add fiber-ai/fiber-ai-plugin --skill enrich
npx skills add fiber-ai/fiber-ai-plugin --skill audience

Each skill teaches the agent the correct authentication, parameter structure, workflow ordering, and error handling for its domain — so generated code is right the first time.

SDK docs via Context7

Both SDKs are indexed in Context7, so any agent with the Context7 MCP server can pull current Fiber SDK documentation — function signatures, parameter types, response shapes — while writing code:

claude mcp add --transport http context7 https://mcp.context7.com/mcp

MCP vs SDKs: when to use which

	MCP server	SDK
Use case	Doing tasks with Fiber inside an AI assistant	Building applications with Fiber
Example	"Find SaaS companies in NYC" in Claude	A Node app that enriches leads from your CRM
How it works	The agent calls Fiber tools on your behalf	Your code calls Fiber functions directly
Auth	`x-api-key` header or `apiKey` in tool calls	`apiKey` in body/query
Best for	Prospecting, ad-hoc searches, exploration	Production apps, pipelines, automations

Use both: prototype a search interactively over MCP, then ship it with the SDK.

Example prompts

Once connected, try:

"Find AI companies in San Francisco with 50–200 employees"
"Get the work email for linkedin.com/in/johndoe"
"Build a list of 100 AI startups in the US and enrich their founders' emails"
"Write a TypeScript script that searches companies and saves results to a database"
"How many credits do I have left?"

Rate limits

Busy periods return HTTP 429 — wait briefly and retry. In production, add exponential backoff, and prefer the audience workflow for bulk work instead of many individual calls. Details in the API docs.

Developing with AI Agents

On this page