Firecrawl ↗
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
INFRASTRUCTURE FOR THE AGENT ECONOMY
Operate a service from a command-line 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 authentication and machine-readable output options before scripting calls. Interpret exit status and output together, especially for paid actions.
Before you proceed: Prefer explicit arguments and budget limits over broad unattended commands.
AI Agent Store editorial selection guidance. Check each listing’s official sources and setup requirements.
FIND THE MISSING CAPABILITY
47 services · Catalog updated 2026-11-10 · See each listing’s review date
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
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
Pay for compatible API services from your authorized wallet.
Authenticate with email OTP; the owner funds the wallet and sets spending limits.
Our integration playbook
Put a budget boundary around each paid API call
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
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
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
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
Retrieve current public web data through a hosted MCP connection.
Create a Bright Data account, configure its API token and approve the public-data scope and usage budget.
Our integration playbook
Check coverage before expanding a public-data collection
Provision Postgres and inspect scoped development databases.
Authorize a Neon account and project, choose database permissions and billing, and review MCP-requested actions before execution.
Our integration playbook
Use an isolated branch to validate a database change
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
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
Keep agent-generated files in managed object storage.
Create a Tigris account, authorize the intended organization and buckets, and choose access and retention settings.
Our integration playbook
Verify the stored object before handing off its link
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
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
Run hosted image, video and audio generation jobs.
Select a fal account or workspace, authorize the connection, fund the required credits and set a permitted model and spending scope.
Our integration playbook
Treat generation as a tracked job with an output contract
Transcribe audio through hosted speech models.
Create a Deepgram project, issue a scoped API key or sign in through the CLI, and choose an audio-processing budget and permitted input files.
Our integration playbook
Keep the transcript traceable to the original audio
Connect agents to email, calendars and meeting records.
Create a Nylas application and connect an authorized account or provision an Agent Account. Grant only the account resources and actions needed for the workflow.
Our integration playbook
Resolve account identity and time zones before booking
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
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
Deploy and inspect application infrastructure through agent tools.
Create a Railway account, choose a workspace and billing plan, and authorize the projects the agent may access. Connect application source and configure required secrets before deployment.
Our integration playbook
Bind the deployment to a project, environment and source revision
Operate hosted applications and databases from an MCP client.
Create a Render account and workspace, connect the intended source repository, choose resource plans and authorize your agent. Select the workspace explicitly before operating resources.
Our integration playbook
Check the supported operation before committing to an MCP workflow
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
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
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
Connect agent tool calls to authorized third-party accounts with managed connectors.
Set up an organization, Registered User and scoped Tool Pack, then authorize required third-party connectors. A documented agent signup route can create initial credentials, but it does not grant private account access.
Our integration playbook
Bind each tool call to the intended user and permission scope
Run hosted application checks and inspect results through MCP, API or CLI.
Create an account, select monitoring locations and a plan, and configure checks and alerts. Authorize an approved OAuth client or issue a key with the required account role.
Our integration playbook
Distinguish a monitor’s last result from current application health
Search synchronized context from authorized apps and databases through API, CLI or MCP.
Create an account and collection, authorize the required source connections and wait for an initial sync. Choose a plan and decide which data the agent may retrieve.
Our integration playbook
Check source freshness before treating retrieved context as current
Query managed analytics data and published endpoints through MCP or APIs.
Create a Workspace in the intended region, ingest an authorized dataset and prepare query endpoints. Issue a resource-scoped token or appropriately restricted JWT and set a usage budget.
Our integration playbook
Give the agent a scoped analytical question and a known data window
Query blockchain nodes and indexed data through MCP, API or CLI.
Create an account and app for API or MCP access, or authorize an EVM wallet and USDC budget for the separate x402 gateway. Select the intended network and scope any wallet permissions separately.
Our integration playbook
Bind blockchain observations to a chain, block and payment route
Run browser-based collection in managed cloud browsers.
Create a Browser API zone, obtain its connection credentials and set a bandwidth budget.
Our integration playbook
Choose hosted rendering for interactive pages
Collect structured search-engine results for agent research.
Create a SERP API zone, configure an API token and choose query locales and usage limits.
Our integration playbook
Build a repeatable search-results collection
Collect structured records with maintained website scrapers.
Create an account and API token, select a scraper or dataset, and define fields, targets and a collection budget.
Our integration playbook
Choose fresh collection or an existing dataset
Turn complex documents into structured fields and layout-aware content.
Create a Reducto account and authorize a key or local login. Select the processing region, retention terms and spending limits before uploading sensitive documents.
Our integration playbook
Validate document evidence before accepting structured fields
Retrieve library documentation and examples for an agent’s coding task.
Connect an MCP client with OAuth or create a Context7 API key. Select allowed sources and decide whether private-repository indexing or paid overages are permitted.
Our integration playbook
Match documentation to the installed dependency before coding
Create and operate conversational video agents through API, MCP and CLI.
Create a Tavus developer account, configure credentials and billing, and choose a face, voice and permitted application tools. Set session duration, concurrency and spending limits.
Our integration playbook
Bound the session lifecycle before connecting application actions
Run agent code in hosted sandboxes with controlled resources and resumable state.
Create an account and select a project and plan. Issue a project API key for SDK use, or authenticate the CLI separately. Set resource limits, timeouts and a budget before scheduling work.
Our integration playbook
Choose the sandbox lifecycle before starting code
Extract structured fields from documents with hosted models and asynchronous API jobs.
Create a Mindee account, configure a model and test representative documents. Issue an organization API key, choose the appropriate plan and processing zone, and lock the production schema before automating imports.
Our integration playbook
Check field meaning before importing extracted data
Supply scoped credentials to agent workloads through managed secrets, CLI and MCP.
Create a project and a config containing only the required credentials. Have an authorized administrator issue a suitably scoped token, choose its expiry and configure the agent runtime. The MCP server requires Node.js 20 or later.
Our integration playbook
Match credential scope to the workload before launching it
Queue, inspect and retry incoming webhooks that trigger agent workflows.
Create an account and project, connect a source to a destination, and configure incoming webhook signature checks and destination authentication. Select throughput and retention appropriate to the workflow.
Our integration playbook
Make event retries safe before connecting them to agent actions
Deploy and scale voice-agent sessions on managed infrastructure.
Create an account and the intended organization, activate billing and configure the application’s model-provider secrets. Prepare an agent image or Dockerfile and choose deployment capacity and transport.
Our integration playbook
Test the full session lifecycle before scaling voice traffic
Deploy custom AI endpoints on managed CPU and GPU compute.
Create a project, configure billing, application dependencies and model secrets, and choose compute and scaling settings. Prepare a tested application and the service-account credentials required for automated deployments.
Our integration playbook
Test access control and resource limits alongside inference output
Retrieve observed internet service banners and host context through API, SDK or CLI.
Create a Shodan account and obtain its API key. Select an entitlement covering the intended search, history or monitoring workload; free key creation does not unlock every method.
Our integration playbook
Separate stored observations from a request to scan an asset
Process audio with hosted leveling, noise reduction and multitrack post-production.
Create an account, select an output preset and authorize an API key or OAuth connection. Choose available processing credits and any intended publishing destinations before running a production.
Our integration playbook
Validate the processed audio before enabling automatic publishing
Geocode address batches and append geographic reference data through API, SDK or CLI.
Create an account and API key, confirm country and field coverage, and choose a plan and usage limit. Self-serve and Enterprise use different accounts and endpoints.
Our integration playbook
Budget by requested fields and review approximate matches before joining datasets
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.