Skip to content
Submit API / MCP
API TRACKER FOR AGENTS

The directory, in plain text.

A lightweight index of APIs, MCP servers, and frameworks for your agent.

llms.txtMarkdown

Loading the published source…

Discover APIs. Build with AI.

Your directory for APIs, AI models, MCP servers, and the tools to connect them.

Try a starting point:
18,249API profiles indexed44,805MCP servers listed17Agent frameworks

LESS SEARCHING. MORE SHIPPING.

A new generation of building blocks

Useful APIs for ambitious ideas. Handpicked, with sources you can check.

Full directory ↗
12 curated APIsCurated summaries reviewed
Anthropic logoAI models

Anthropic

Build assistants that reason, write code, and use tools with the Claude API.

Language modelsTool use
Documentation ↗Source reviewed
Firecrawl logoSearch & data

Firecrawl

Turn websites into structured data and readable content for AI applications.

Web scrapingExtraction
Documentation ↗Source reviewed
Exa logoSearch & data

Exa

Search the web and retrieve page content for AI research and agent workflows.

Web searchResearch
Documentation ↗Source reviewed
Supabase logoDeveloper tools

Supabase

Connect AI tools to your Supabase projects to query data and manage development workflows.

DatabaseMCP
Documentation ↗Source reviewed
Stripe logoBusiness APIs

Stripe

Give AI assistants access to Stripe tools for payments and business operations through MCP.

PaymentsMCP
Documentation ↗Source reviewed
ElevenLabs logoVoice & audio

ElevenLabs

Add speech generation, transcription, and conversational voice experiences to your app.

Text to speechVoice agents
Documentation ↗Source reviewed
Resend logoBusiness APIs

Resend

Send transactional emails from your application with an API built for developers.

EmailNotifications
Documentation ↗Source reviewed
Cohere logoAI models

Cohere

Build enterprise AI with language models, embeddings, and reranking for retrieval workflows.

EmbeddingsReranking
Documentation ↗Source reviewed
Pinecone logoSearch & data

Pinecone

Store and search vector data to retrieve relevant context for AI applications.

Vector databaseRetrieval
Documentation ↗Source reviewed
Tavily logoSearch & data

Tavily

Search the web and extract content for research agents and AI applications.

Web searchResearch
Documentation ↗Source reviewed
Groq logoAI models

Groq

Run supported language and audio models through Groq’s inference API.

InferenceAudio
Documentation ↗Source reviewed
Notion logoDeveloper tools

Notion

Connect AI assistants to workspace content using Notion’s hosted MCP server.

KnowledgeMCP
Documentation ↗Source reviewed

There’s a whole ecosystem out there.

Explore the full API directory →

START WITH AN IDEA

What are you building?

A few thoughtful starting points. Your next stack is in here.

✳COLLECTION / 01

Build an AI agent

Connect a model to useful context and real-world actions.

11 building blocks ↗⌕COLLECTION / 02

Give your AI the web

Search, extract, and retrieve the context your application needs.

5 building blocks ↗≋COLLECTION / 03

Build with voice

Bring speech and conversation into your next product.

2 building blocks ↗⌘COLLECTION / 04

Connect your coding agent

Bring project context and tools into your development workflow.

3 building blocks ↗

MAKE AN INFORMED CHOICE

Good options. Clearer decisions.

Explore provider differences before you commit.

OPEN SOURCE · BY APIDECK

From discovery to shipping.

Explore developer tools →
API testing

Portman

Turn OpenAPI specifications into Postman collections with contract and variation tests. Run them with Newman in your CI pipeline.

OpenAPIPostmanContract testingCLI
Explore Portman →
Agent infrastructure

MCP Connect

Connect MCP servers, namespace their tools, and route tool calls to the right server. Bring your own storage, OAuth providers, and agent framework.

MCPTypeScriptTool callingOAuth
Open MCP Connect →Explore MCP Connect →

APIDECK EXPERIENCE LAB

IN THE LAB · COMING SOON

API vs. MCP.
Put it to the test.

Direct API calls or MCP tools: the same task, two paths. We’re measuring correctness, latency, tokens, and cost.

For API-backed MCP tools. Results and methodology coming soon.

An agent calls an API directly or uses an MCP server that calls the API. Both routes reach the same service. Benchmark results coming soon.AGENT TASKDirect APIHTTP requestsMCPTool callsAPI requestvsSAME SERVICE
CorrectnessLatencyTokensCost

A LITTLE CONTEXT

Better questions.
Better building blocks.

How we curate the directory ↗
What is API Tracker?+

API Tracker is a directory for discovering APIs, developer tools, and MCP servers. Browse provider profiles, explore documentation and SDKs, or use curated collections to find tools for a specific project.

What is the difference between an API and an MCP server?+

An API defines how software accesses a service. An MCP server exposes tools and context using the Model Context Protocol so compatible AI clients can discover and use them. An MCP server often calls an existing API behind the scenes.

How should I choose an API for an AI agent?+

Start with the task your agent needs to complete. Compare documentation, authentication, tool permissions, rate limits, pricing, and reliability. Test with your own workload, and check MCP support when your chosen client uses it.

How fresh is the directory data?+

The curated discovery entries show a review date and link to the provider documentation used for their summaries. The wider catalog is maintained separately and may have different update dates. A review date is not a guarantee of uptime or unchanged pricing; check the provider’s documentation before integrating.

FROM IDEA TO INTEGRATION

The next big thing starts
with a building block.

Find yours ↗

Search API Tracker

Curated starting points

↑ ↓ navigate · Enter openBrowse all APIsMCP servers