A1 ratingsCloudflareCloudflare Agents SDK

Cloudflare Agents SDK

Cloudflare · framework · Any industry
A
AGrade
74Score
±1395% range
≈#29Rank of 1134
0%From fleets
FR-CAT-00926Catalog no.

The six pillars

Each bar is the score; the bracket is its 95% range.

Can you see what it costs?

Vendor cost API (Cloudflare Billable Usage API (GET/POST accounts/{id}/billable/usage, FOCUS v1.3; Alpha, Restricted)) · prices published
75±38
Desk research 100 · counts for 25% · A cost API you can call scores highest; an admin console or cloud billing export next; a card statement or emailed invoice is all some products leave you. Published prices add to it.

Can you see how much it's used?

Cloudflare GraphQL Analytics API (per-Worker/DO metrics)
86±27
Desk research 100 · counts for 15% · A usage API (tokens, seats, credits, conversations) a buyer can read.

Can you tie cost to one agent?

By project
64±27
Desk research 70 · counts for 15% · Exact (one key or project per agent) beats by-project, by-workspace or by-user.

Can an agent on it report out?

Remote MCP connector · Cloudflare ships managed remote MCP servers (mcp.cloudflare.com/mcp, GraphQL, Observability); agents on Workers can also call HTTP out directly.
86±27
Desk research 100 · counts for 15% · A remote MCP connector scores highest, then a local MCP server, an SDK, an API or a workflow step; copy-and-paste lowest. Any open standard counts, not just FleetRegistry.

Can you control spend and access?

Spend cap: None · Per-agent keys: One shared key · Audit log: None · Revoke: None · SSO: None
25±38
Desk research 0 · counts for 20% · Hard spend caps (30%), scoped per-agent keys (25%), an audit log you can read by API (20%), revoking by API (15%), SSO with SCIM (10%).

Does it work on small plans?

Small plans get the data
86±27
Desk research 100 · counts for 10% · Whether the plan a person or small business buys gets the cost and usage data at all.

Where the evidence comes from

Independent fleets0%Desk research66%Neutral starting point34%

Once three independent fleets report on a pillar, desk research counts for at most a third of it. FleetRegistry's own fleets never count.

Controls on record

Spend capNone
Per-agent keysOne shared key
Audit logNone
RevokeNone
SSONone
PricesPublished

Open-source framework that provides no controls itself; agents deployed on Workers inherit Cloudflare account controls (a Workers spending limit can block new invocations at a threshold, scoped tokens, API audit logs).

History

11-12 A 7411-13 A 7411-14 A 7411-15 A 7411-16 A 7411-17 A 7411-18 A 7411-19 A 74
First rated 2026-10-02 at 76 (A). Now 74. Published grades are sealed daily into the transparency log (N4.4). Grade held since 2026-10-02.

Every fact, with its rung and source

Each fact stands on its own source and its own rung of the evidence ladder (Rule N2.1). Verified Observed Declared Inferred. The weakest fact in a pillar sets its weight.

FactValueRungCheckedSources
How a buyer sees cost
Cost
Vendor cost API Declared
medium confidence
2026-11-17
2 earlier
[1][2][3] Correct
Prices published
Cost
Yes Inferred 2026-11-17
3 earlier
[1][2] Correct
Usage API
Usage
Cloudflare GraphQL Analytics API (per-Worker/DO metrics) Declared
medium confidence
2026-11-17
2 earlier
[1][2][3] Correct
Cost per agent
Per agent
By project Declared
medium confidence
2026-11-17
2 earlier
[1][2][3] Correct
How an agent reports out
Reports out
Remote MCP connector Declared
medium confidence
2026-11-17
2 earlier
[1][2][3] Correct
Per-agent keys
Controls
One shared key Inferred 2026-11-17
3 earlier
[1][2] Correct
Audit log
Controls
None Inferred 2026-11-17
3 earlier
[1][2] Correct
Revoke access
Controls
None Inferred 2026-11-17
3 earlier
[1][2] Correct
Spend cap
Controls
None Inferred 2026-11-17
3 earlier
[1][2] Correct
SSO
Controls
None Inferred 2026-11-17
3 earlier
[1][2] Correct
Small plans get the data
Small plans
Yes Declared
medium confidence
2026-11-17
2 earlier
[1][2][3] Correct

Prices · SDK is free; bills as Workers/Durable Objects/AI usage on the account

Notes · Cost API: GET /accounts/{account_id}/billable/usage is labelled 'Alpha, Restricted' in the API reference; FOCUS v1.3-aligned daily records per account per metric (max 31-day range); GET returns usage only, rated cost via POST with Metric: cost. Billable Usage dashboard is Pay-as-you-go only. Attribution is per Worker/service via GraphQL, not per agent instance.

Scored with the rubric for Open-source frameworks (Rule N7.1). Each pillar blends a neutral 50, desk facts weighted by rung, and independent fleets. A1 is 85+ with fleet proof, A 70, B 55, C 40, D 25, E below. Part N of the Rules

Run agents on Cloudflare Agents SDK?

Give each one a permanent number, a named person who answers for it, and a record of what it can touch and what it costs. Free.