Skip to main content
hc
Submit
toolsSource-backedReview first Safety · Privacy ·
Cloudflare logo

Cloudflare Agents SDK

Cloudflare framework for building, deploying, and running AI agents on Workers with durable platform primitives.

by Cloudflare·added 2026-04-27·
CLI
HarnessCLI
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/tools/cloudflare-agents-sdk
Source URLs
https://developers.cloudflare.com/agents/, https://github.com/cloudflare/agents
Brand
Cloudflare
Brand domain
developers.cloudflare.com
Brand asset source
brandfetch
Author
Cloudflare
Claim status
unclaimed
Last verified
2026-04-27

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Required checks are still incomplete. Finish source and safety verification before adopting this resource.

Compare context
Selected

0

Current score

58

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Required checks missing

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    No safety notes listed.

    Pending

  • Privacy notes presentRequired

    No privacy notes listed.

    Pending

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

Copy & paste

Copy-ready — paste the snippet to get started.

Install command

Not provided

Config snippet

Not provided

Copy snippet

Provided

Prerequisites

None

Platforms

1 listed

Install type

Copy & paste

Adoption plan

Balanced adoption plan

Current risk score 44/100. Use staged verification before broader rollout.

Risk 44
Adoption blockers
  • Safety notes are missing.
  • Privacy notes are missing.

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    Listing has review metadata.

    Done

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes missing; review source code paths before execution.

    Pending

  • Review privacy notesRequired

    Privacy notes missing; inspect network/data behavior manually.

    Pending

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Safety notes. Risk score 36.

Risk 36

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Missing

Safety notes are missing.

Required in this preset

Privacy notes

Missing

Privacy notes are missing.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Safety notes

Decision timeline

Decision timeline · balanced

Blocking gaps: Review safety notes. Risk 32.

Risk 32

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are missing.

Pending

verify

Review privacy notes

Privacy notes are missing.

Pending

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Review safety notes

Schema details

Install type
copy
Troubleshooting
No
Source repository stats
Scope
Source repo
Tool listing metadata
Pricing
freemium
Disclosure
editorial
Application category
DeveloperApplication
Operating system
Web
Full copyable content
## Editorial notes

Cloudflare Agents SDK is relevant for teams that want agent runtimes close to edge compute, durable objects, and serverless deployment.

## Disclosure

Editorial listing. No paid placement or affiliate link is used.

About this resource

Editorial notes

Cloudflare Agents SDK is relevant for teams that want agent runtimes close to edge compute, durable objects, and serverless deployment.

Disclosure

Editorial listing. No paid placement or affiliate link is used.

#agent-framework#cloudflare

Source citations

Add this badge to your README

Show that Cloudflare Agents SDK is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/tools/cloudflare-agents-sdk.svg)](https://heyclau.de/entry/tools/cloudflare-agents-sdk)

How it compares

Cloudflare Agents SDK side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

3 trust signals differ across this comparison (Package trust, Source provenance, Submitter).

Next steps differ across entries — use the actions in the table below to copy install commands and source links per resource.

Field
Cloudflare logoCloudflare Agents SDK

Cloudflare framework for building, deploying, and running AI agents on Workers with durable platform primitives.

Open dossier
Cloudflare logoCloudflare AI App Builder

A source-backed Cloudflare collection for building AI apps on the edge: combine Workers, Workers AI, Agents, D1, KV, R2, Wrangler deployment operations, and Cloudflare MCP access with explicit environment and data boundaries.

Open dossier
Cloudflare logoBuild Cloudflare Workers AI Agents With Durable State

A practical architecture guide for building AI agents on Cloudflare Workers with Workers AI inference and durable per-agent state. Use the Agents API, Durable Objects, bindings, and Workers observability to keep agent sessions reliable across requests.

Open dossier
Cloudflare logoCloudflare MCP Server - MCP Servers

Build applications, analyze traffic, and manage security settings through Cloudflare

Open dossier
Next stepsDiffers
Open dossierAPI JSONOpen LLMOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustDiffersPackage not verifiedPackage not verifiedPackage not verifiedPackage verified
Source provenanceDiffersSource-backedSource-backedSource-backedNo submission link
SubmitterDiffers—MkDev11MkDev11—
Install riskReview firstReview firstReview firstLow risk
Notes Safety · Privacy · Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandCloudflare logoCloudflareCloudflare logoCloudflareCloudflare logoCloudflareCloudflare logoCloudflare
Categorytoolscollectionsguidesmcp
Sourcesource-backedsource-backedsource-backedfirst-party
AuthorCloudflareMkDev11MkDev11Cloudflare
Added2026-04-272026-06-042026-06-042025-09-18
Platforms
CLI
Claude Code
Claude Code
Claude CodeClaude Desktop
Source repo————
Safety notes— missing✓This collection runs nothing itself; linked entries can deploy Workers, inspect Cloudflare resources, or change app configuration. Use preview/staging environments and scoped API tokens before allowing Claude-assisted deployment or MCP operations. Review storage consistency, cache behavior, and rollback plans before moving AI workflows to production traffic.✓Keep model output reviewable before it triggers irreversible product actions, external messages, or billing-sensitive work. Store only the durable state the agent needs; avoid persisting full prompts, files, or transcripts when summaries or structured state are enough. Add idempotency and replay handling for events that may retry, arrive out of order, or resume after an agent instance restarts.✓Use a least-privilege Cloudflare token because DNS, security, Worker, and deployment actions can affect production services.
Privacy notes— missing✓The collection stores no data itself; linked Cloudflare resources may process prompts, user requests, logs, analytics, object storage, or database rows. Workers AI and external model calls may involve account-level telemetry and provider-specific retention rules. Do not paste production secrets, customer data, or Cloudflare API tokens into transcripts or PR comments.✓Workers logs, Durable Object storage, Workers AI prompts, model outputs, request headers, and bound service data may contain user or business context. Redact sensitive fields before logging and define retention for prompts, intermediate reasoning, tool results, and conversation state. Separate staging and production state so test prompts and generated outputs cannot leak into live sessions.✓Zone settings, analytics, logs, account identifiers, deployment metadata, and security configuration may be sent through model context.
Prerequisites— none listed
  • A Cloudflare account, Wrangler authentication, and a target account/project for development or staging.
  • Agreement on which resources use Workers AI, Agents, D1, KV, R2, Queues, or external APIs.
  • Separate secrets and environment bindings for local, preview, staging, and production deployments.
  • A Cloudflare account with Workers, Workers AI, and Durable Objects available for the target environment.
  • Wrangler and a Worker project configured for TypeScript or JavaScript.
  • A clear state boundary, such as one agent per user, workspace, conversation, job, or document.
  • Test prompts, expected model responses, and sample state transitions for local or staging validation.
  • Cloudflare account with active zones
  • Cloudflare API Token from https://dash.cloudflare.com/profile/api-tokens
  • Cloudflare Account ID (found in Cloudflare dashboard)
  • Node.js and npm/npx available for running the @cloudflare/mcp-server-cloudflare package
Install———
claude mcp add cloudflare --env CLOUDFLARE_API_TOKEN=YOUR_TOKEN --env CLOUDFLARE_ACCOUNT_ID=YOUR_ACCOUNT_ID && claude mcp list
Config———
{
  "mcpServers": {
    "cloudflare": {
      "env": {
        "CLOUDFLARE_API_TOKEN": "${CLOUDFLARE_API_TOKEN}",
        "CLOUDFLARE_ACCOUNT_ID": "${CLOUDFLARE_ACCOUNT_ID}"
      },
      "args": [
        "-y",
        "@cloudflare/mcp-server-cloudflare"
      ],
      "command": "npx",
      "type": "stdio"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.