INFRASTRUCTURE FOR THE AGENT ECONOMY
Use a provider library from your runtime.
Check capabilities, credentials, costs, and required human setup. Read the integration instructions, then connect through the provider’s API, SDK, MCP, or CLI.
Check the supported language and version against the official quickstart. Confirm configuration and response handling with a small controlled task.
Before you proceed: A convenience method still consumes the underlying service’s permissions and usage.
AI Agent Store editorial selection guidance. Check each listing’s official sources and setup requirements.
FIND THE MISSING CAPABILITY
68 services · Catalog updated 2026-10-27 · See each listing’s review date
Create and operate your own email inboxes.
Agent signup can receive mail; a human must connect the account before sending is unlocked.
Our integration playbook
Build an inbox workflow that separates receiving from sending
Launch a cloud browser to interact with websites.
Provision a provider account and API key; target sites may require login.
Our integration playbook
Choose session control before building a browser workflow
Delegate a web task or control a managed browser.
Provision a cloud API key and any target-site credentials.
Our integration playbook
Decide whether to delegate a task or control the browser
Search the web and retrieve page contents for your research.
Provision an API key and usage budget.
Our integration playbook
Build a research record you can audit later
Find web information through search designed for AI agents.
Sign up for an API key; approve paid usage beyond the included allowance.
Our integration playbook
Set a research budget before expanding the search
Turn websites into Markdown and structured data you can use.
A limited introductory scrape is documented without a key; higher limits require an account.
Our integration playbook
Validate extraction before scaling to a whole website
Run your code in an isolated execution environment.
Provision an API key and approve the compute budget.
Our integration playbook
Treat the sandbox lifecycle as part of the task
Discover app tools and use the access your owner has authorized.
Connect a provider account and authorize each application and scope needed.
Our integration playbook
Bind each tool call to the right connected account
Save useful context and recall it across your sessions.
Provision an API key and decide which user or agent owns each memory.
Our integration playbook
Design memory boundaries before saving context
Discover and run maintained data-collection tools in the cloud.
Authorize an Apify account with OAuth or an API token; optional agent payment routes require approved funds.
Our integration playbook
Verify an Actor before trusting a data pipeline
Provision an isolated cloud computer for your code and tools.
Create a Daytona organization, provision an API key and approve resource usage and billing.
Our integration playbook
Make sandbox cleanup part of your result
Call authorized application tools through a scoped agent session.
Configure Nango, have account owners authorize their integrations, and create a session restricted to the intended tenant and tools.
Our integration playbook
Prove tenant isolation before enabling application writes
Request cited web research and structured enrichment for your task.
Provision a Parallel API key and usage budget, or configure an authorized payment method for the separate payment gateway.
Our integration playbook
Keep the research evidence attached to each output field
Run durable background tasks beyond your current agent session.
Create an organization and project, authorize CLI access, deploy task code and configure the required secrets.
Our integration playbook
Separate a durable run from a repeatable external action
Build persistent context from conversations and business activity.
Create a Zep account and API key; map application users and authorize which records may be ingested.
Our integration playbook
Check that memory changes when the underlying facts change
Turn complex documents into text and structured data your agent can inspect.
Create an account, provision an API key and approve uploading the documents and using processing credits.
Our integration playbook
Validate the difficult page before processing the whole collection
Prepare connected document collections for retrieval workflows.
Create an account and API key; authorize source and destination connectors and approve processing costs.
Our integration playbook
Reconcile source files with the destination records
Retrieve cited context from your authorized document collection.
Create a Pinecone account and API key, create an assistant, and upload documents you are authorized to process.
Our integration playbook
Test retrieval separately from answer generation
Allocate isolated compute for generated code and custom dependencies.
Create a Modal account and workspace, configure credentials, and authorize the compute budget and any required secrets.
Our integration playbook
Budget the environment before executing generated code
Call app tools using the accounts your users authorize.
Create a Connect project and OAuth client; have each user connect the intended accounts and approve production billing.
Our integration playbook
Prove which user owns the connected account
Run browser tasks on managed browser capacity.
Create a Browserless account, authorize OAuth or configure a token, and choose a plan with suitable session limits.
Our integration playbook
Choose a session lifetime that matches the task
Find current web sources and return evidence in a useful structure.
Provision an API key and account credits, or configure an approved funded wallet and spending policy for the documented x402 route.
Our integration playbook
Validate a citation before spending on deeper research
Give your agent a managed browser with live session controls.
Create a Kernel account and API key; authorize the target websites, account access and resource budget.
Our integration playbook
Recover the existing browser before opening another
Execute coding tasks in managed development sandboxes.
Create a Runloop account and scoped API key; approve repository access, environment inputs and resource spending.
Our integration playbook
Keep environment identity with each coding result
Connect agent workflows to live voice conversations.
Create a Vapi account and API key, configure an assistant and authorized number or web calling, and approve recipients and spending.
Our integration playbook
Verify the business action separately from the conversation
Extract structured web data and maintain scheduled collections.
Provision an API key and credit budget, or use the documented MPP route with an approved funded InFlow wallet and spending policy.
Our integration playbook
Validate a sample before scheduling a collection
Use authorized app tools through a managed actions runtime.
Create an Arcade account, choose the tools for your workflow and obtain the account owner’s OAuth authorization.
Our integration playbook
Bind each tool call to the correct account owner
Start cloud browser tasks with a documented agent-access flow.
Agent Access documents a challenge-based trial key without a dashboard account. Target-account access and any paid expansion still need owner authorization.
Our integration playbook
Treat trial onboarding and browser permissions separately
Retrieve evidence from your authorized documents through a managed RAG API.
Create an organization and namespace, generate an API key and approve the documents to ingest.
Our integration playbook
Prove retrieval with known answers before adding a corpus
Run generated code through an isolated code-interpreter API.
Create a Riza account and API key; choose the runtime, input data, permitted network access and spending limit.
Our integration playbook
Use a bounded transformation before executing generated tools
Trigger structured notification workflows from your agent.
Create a Knock account, configure delivery providers and recipient data, and authorize the workflows your agent may trigger.
Our integration playbook
Expose one notification workflow with a defined payload
Maintain shared task state in a managed Redis database.
Create and authorize a database, or use the documented agent scratch-database route. Scratch databases expire after 72 hours unless claimed through an Upstash account.
Our integration playbook
Define key ownership and expiry before sharing agent state
Send transactional email from an authorized domain.
Create an account, verify the sending domain through its DNS, and authorize credentials and intended recipients.
Our integration playbook
Track the message outcome before retrying delivery
Upload, transform and deliver managed media assets.
Choose a Cloudinary product environment and authorize access. An agent can provision a temporary Claimable Cloud, but a person must claim it with email verification to retain it.
Our integration playbook
Verify the delivered variant before publishing its URL
Obtain delegated access to APIs on a user’s behalf.
Configure an Auth0 tenant, application and external provider connection. Each user must authenticate and grant the required provider permissions.
Our integration playbook
Bind every external action to the correct user and grant
Inspect and operate a hosted application backend.
Create a project and deployment, define application functions and provision credentials scoped to the intended deployment.
Our integration playbook
Separate deployment selection from permission scope
Search web and specialist research sources through one API.
Create a Valyu account, obtain an API key or authorize MCP sign-in, and select a plan with access to the datasets your task needs.
Our integration playbook
Keep source coverage visible throughout the research task
Maintain a hosted vector index for retrieval and agent memory.
Create a managed cluster, choose its region and capacity, define the collection and embedding model, and supply a database API key scoped to the intended collections.
Our integration playbook
Validate retrieval boundaries before loading the full corpus
Resume agent workflows after failures and long waits.
Create an Inngest account, integrate the SDK and deploy or connect the application code that executes your functions. Scope agent access to the intended environment.
Our integration playbook
Make each external side effect recoverable before enabling retries
Coordinate availability and scheduling across authorized calendars.
For MCP, create a Scheduler account and developer application in the correct data center. Connect the calendars and select an internal or multi-tenant authorization model.
Our integration playbook
Resolve participants and authorization before proposing a time
Give agents API access to telephone and messaging infrastructure.
Create and fund a Telnyx account, issue a V2 API key and configure the numbers, messaging or voice resources required for your workflow. Complete applicable provider onboarding before production use.
Our integration playbook
Separate resource inspection from outbound communication
Preserve workflow progress across worker failures and long waits.
Create a Temporal Cloud account and namespace, choose API-key or mTLS authentication, and deploy workers containing the workflow and activity code.
Our integration playbook
Design recovery around the external action, not just the workflow
Maintain vector and text retrieval over a hosted search index.
Create an account and API key, select a region and namespace, and define document identifiers, searchable fields and the embedding approach for your corpus.
Our integration playbook
Test access filters and cold retrieval before scaling the corpus
Deliver webhook events and investigate failed deliveries with agent tools.
Create a Svix account, select an environment and configure an application and receiver endpoint. Enable App Portal MCP in each intended environment before issuing an application-scoped agent token.
Our integration playbook
Make the receiver safe to replay before recovering missed events
Manage identity resources and authorize access to your MCP services.
Create a WorkOS workspace, select staging or production, configure the application and identity connections, and approve the agent’s dashboard account access. Production requires billing information.
Our integration playbook
Keep management authorization separate from end-user access
Stream agent responses across reconnecting clients and multiple devices.
Create an Ably account and application, configure channel rules and retention, and integrate the transport SDK with your model workflow. Provide a server-side token endpoint and conversation-level authorization.
Our integration playbook
Prove reconnection and conversation isolation with the same response
Send authorized messages and track delivery through telecom infrastructure.
Create and verify a Twilio account, configure an eligible sender or Messaging Service, and complete destination-specific registration where needed. Establish recipient permission and billing before live sends.
Our integration playbook
Reconcile message identity before retrying an uncertain send
Run realtime voice agents on managed media and deployment infrastructure.
Create a LiveKit Cloud project, choose a plan, prepare a working agent and configure its secrets. Link the CLI to the intended project and implement an authenticated token endpoint for production clients.
Our integration playbook
Verify dispatch, media flow and shutdown as separate session states
Generate and transcribe speech through hosted voice models and agent tools.
Create a Cartesia account, select a usage plan and obtain server credentials or sign in through the MCP connection. Choose the voice, model and audio format required by the destination.
Our integration playbook
Match the audio contract before connecting speech to a live workflow
Operate notification workflows and subscriber preferences through agent tools.
Create a Novu Cloud account in the intended region, configure a development environment and connect the required delivery providers. Define subscriber identifiers, preferences and the workflow before enabling real recipients.
Our integration playbook
Resolve the subscriber, environment and delivery provider before triggering
Give agents scoped, consented access to your application through OAuth.
Create a Stytch project, configure the connected client, redirect URLs and scopes, and implement the consent and token-validation flow. For an existing identity provider, configure a Trusted Auth Token profile and claim mapping.
Our integration playbook
Test the denied path as carefully as the successful authorization
Run model inference for agent workflows on managed serving capacity.
Create a Fireworks account and API key, configure billing and choose a supported model and serving mode. Set an application budget and decide which tools the model may propose.
Our integration playbook
Separate model inference from permission to execute a tool
Manage notification templates, journeys and delivery through operational agent tools.
Create a Courier workspace, connect delivery providers and prepare a test recipient. Select the Test environment and issue a separate API key for the agent before allowing production sends.
Our integration playbook
Resolve environment and provider capacity before releasing a notification
Call hosted models on managed inference capacity for agent workloads.
Create an account and project, generate an API key, configure billing and choose the exact model and serving mode. Define the request budget and validate the model on the intended task.
Our integration playbook
Choose the serving mode before committing to a latency-sensitive workflow
Run browser sessions with saved profiles and natural-language page operations.
Create an Airtop account, obtain a developer API key and select a usage plan. For authenticated sites, have the authorized user establish a profile through the supported login flow.
Our integration playbook
Verify profile identity and session cleanup before repeating browser work
Turn approved documents into physical letters and postcards through an API.
Create a Lob account and prepare sender, recipient and print-ready content. Use a Test key for layout and integration checks; an administrator must configure payment before live Print and Mail requests.
Our integration playbook
Separate proof approval from the irreversible physical-mail handoff
Fetch live web content through managed scraping, browser and extraction tools.
Create a Scrapfly account and project, obtain credentials or authorize the MCP connection, and choose the credit plan and project access settings for the workload.
Our integration playbook
Validate page identity and extraction completeness before scaling retrieval
Give agents hosted browser sessions with reusable authenticated state.
Create a Notte account and workspace, select a plan and authorize the MCP connection or issue an API key. Establish any required website login with the authorized account owner.
Our integration playbook
Check authentication, task completion and browser shutdown separately
Match company identifiers against a maintained business dataset.
Create a People Data Labs account, obtain an API key and select Company API credits and field access. Confirm that the intended storage and downstream use fit the account’s agreement.
Our integration playbook
Resolve company identity before writing enrichment into your system
Turn recorded or live audio into transcripts through hosted speech models.
Create an account, obtain an API key and configure funds and alerts for the intended usage. Choose the audio workflow, model and optional features, and ensure the audio is authorized for processing.
Our integration playbook
Keep the audio job identity through transcription and downstream analysis
Run supported language models on managed Cerebras inference infrastructure.
Create a Cloud Console organization and project, issue an API key and configure billing. Select an available model and check its capabilities, project limits and serving option.
Our integration playbook
Budget output tokens against both inference spend and available quota
Run supported models through managed inference APIs and SDKs.
Create a Groq account and API key. Choose an available model and configure the organization’s tier, payment method and spend limits before production use.
Our integration playbook
Coordinate model calls across agents sharing one organization
Convert files through hosted import, processing and export jobs.
Create an account, choose credits and issue an API key with only the required task scopes. Select formats, engine options and the export destination.
Our integration playbook
Verify the exported artifact before declaring conversion complete
Upload, transform and deliver files through managed APIs and a CDN.
Create a project and obtain its public and secret keys. Choose a plan, configure storage behavior and select the transformations and delivery access the workflow needs.
Our integration playbook
Track upload, storage and delivery as separate states
Look up public IP addresses using maintained network and location data.
Create an IPinfo account, choose the data tier and configure overage billing. Authorize the MCP client or issue a server-side API token.
Our integration playbook
Keep network evidence separate from decisions about people
Generate paginated PDF documents through a hosted rendering API.
Create an account, retrieve the API key and choose a document plan. Prepare HTML and accessible assets, then test the intended rendering pipeline before production generation.
Our integration playbook
Validate page content as well as successful PDF generation
Operate video ingest, streaming and playback through APIs or MCP.
Create an account and select the intended environment, token permissions and billing plan. Decide whether playback must be public or signed before creating assets.
Our integration playbook
Keep video creation, readiness and playback permission distinct
Retrieve carrier rates, purchase authorized labels and follow shipment tracking.
Create an account, set up the EasyPost Wallet and ship-from address, and obtain separate test and production keys. Enable wallet carriers or connect authorized carrier accounts, with an approved postage budget.
Our integration playbook
Separate the shipping quote from the paid label and carrier handoff
NO BROWSER REQUIRED
Search for a capability, then follow the listing’s siteGuide link for our original integration playbook: selection advice, workflow, acceptance checks and recovery steps. The complete playbook is in the page HTML, so you can fetch it without JavaScript or a login.
GET /api/agent-services?capability=email GET /api/agent-services?interface=mcp GET /api/agent-services?payment=x402-wallet GET /api/agent-services?payment=mpp-wallet GET /api/agent-services?payment=no-payment GET /api/agent-services?id=e2b
Full catalog: /data/agent-services.json
Manifest: /.well-known/agent-services.json
You are here to get something done. Find a mailbox for your messages, a browser for your web tasks, a sandbox for your code, or a wallet for approved payments.
Inspect the setup requirements before connecting. You may need your owner to create an account, grant OAuth consent, fund a wallet, or provide a website login.
Check whether usage is free, billed to a provider account or uses a documented x402 or MPP wallet. “Not verified” means agent payment support has not been established. Confirm current terms and stay within your owner’s approved budget.