Directory
A public trust score for every agent endpoint, so you know what you are connecting to.
Every known agent endpoint assessed on a published rubric: operator identity and jurisdiction, permission scopes requested against what the stated function requires, data handling and retention policy, authentication and transport security, incident and disclosure history, maintenance signals, and…
- 2,000 endpoints scored
- Published methodology adopted or cited in at least three enterprise procurement policies
- 60 verified operator profiles
Filter the way you actually choose
Free and public forever, with the full methodology published so scores can be disputed on the evidence rather than treated as opinion. Runs in your browser. No account, no card, no call.
Cobalt Works
VerifiedCollaboration · Middle East & Africa
Cobalt Works is a collaboration tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Flat rate
- Free tier
- Yes
- SOC 2
- Type II
$601checked 2026-09-01 · Vendor pricing page5.0 / 5Delta HQ
VerifiedData infrastructure · North America
Delta HQ is a data infrastructure tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Freemium
- Free tier
- No
- SOC 2
- Type II
$547checked 2026-06-22 · Operator survey5.0 / 5Granite Works
VerifiedSecurity · Europe
Granite Works is a security tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Flat rate
- Free tier
- Yes
- SOC 2
- Type I
$313checked 2026-05-05 · Vendor pricing page4.9 / 5Drift HQ
Automation · Asia-Pacific
Drift HQ is a automation tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Freemium
- Free tier
- No
- SOC 2
- Type I
$259checked 2026-02-26 · Operator survey4.9 / 5Keystone Works
VerifiedAnalytics · Latin America
Keystone Works is a analytics tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Flat rate
- Free tier
- Yes
- SOC 2
- None
$25checked 2026-01-09 · Vendor pricing page4.8 / 5Harbor HQ
VerifiedDeveloper tools · Middle East & Africa
Harbor HQ is a developer tools tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Freemium
- Free tier
- No
- SOC 2
- None
$691checked 2026-07-02 · Operator survey4.8 / 5Ember IO
Analytics · North America
Ember IO is a analytics tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Per seat
- Free tier
- Yes
- SOC 2
- None
$637checked 2026-04-23 · Trust centre4.8 / 5Lattice HQ
VerifiedData infrastructure · Europe
Lattice HQ is a data infrastructure tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Freemium
- Free tier
- No
- SOC 2
- Type II
$403checked 2026-03-06 · Operator survey4.7 / 5Ion IO
VerifiedCollaboration · Asia-Pacific
Ion IO is a collaboration tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Per seat
- Free tier
- Yes
- SOC 2
- Type II
$349checked 2026-09-27 · Trust centre4.7 / 5Pinnacle HQ
Automation · Latin America
Pinnacle HQ is a automation tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Freemium
- Free tier
- No
- SOC 2
- Type I
$115checked 2026-08-10 · Operator survey4.6 / 5Meridian IO
VerifiedSecurity · Middle East & Africa
Meridian IO is a security tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Per seat
- Free tier
- Yes
- SOC 2
- Type I
$61checked 2026-05-03 · Trust centre4.6 / 5Quarry IO
VerifiedAnalytics · Europe
Quarry IO is a analytics tool. Pricing, limits and security posture below were read off the vendor's own published pages.
- Pricing model
- Per seat
- Free tier
- Yes
- SOC 2
- None
$493checked 2026-01-07 · Trust centre4.5 / 5
Every qualifying entry is listed and placement cannot be bought. Each record shows the date it was last checked and where the data came from. Found something wrong? Corrections are handled in public.
The problem
Connecting an agent to a third-party service grants it credentials and the ability to act.
There is no equivalent of a security review for these endpoints, no public record of who operates them, what permissions they demand, whether they have been audited, or what they do with data.
Enterprises are either blocking everything or approving blindly.
Who this is for
Security teams building allowlists, developers choosing which agent services to trust, and enterprises writing procurement policy for agent integrations. Also the vendors who need to demonstrate trustworthiness.
What you actually get
Six things that are true on the first day, not on the roadmap.
Complete, not curated-for-ads
Every qualifying entry is listed. Placement cannot be bought on PublicACP.
Checked and dated
Each record carries the date it was last verified and where the data came from.
Filter the way you actually search
Cross-filter on the attributes that decide the choice, not just name and category.
Corrections in public
Anyone can file a correction and see what happened to it. The edit history is open.
Structured data out
Every page ships structured data, and the full dataset is downloadable.
No dark patterns
No fake urgency, no gated contact details, no pay-to-remove-a-competitor.
How it works
Three steps, and the first one costs nothing.
- 01
Run the free tool
Free and public forever, with the full methodology published so scores can be disputed on the evidence rather than treated as…
- 02
See your own numbers
Every known agent endpoint assessed on a published rubric: operator identity and jurisdiction, permission scopes requested against what the stated…
- 03
Upgrade only if it earns it
Keep the free result either way. Move to a paid plan when PublicACP is already doing the work.
Pricing
Published in full. No “contact us for pricing”, no per-seat surprise on renewal.
Free
The wedge, free forever. Enough to run on.
- Free and public forever, with the full methodology published so scores can be disputed on…
- No credit card
- Core loop included
- Community support
Pro
For security teams building allowlists, developers choosing…
- Everything in Free
- Unlimited usage
- Full history and exports
- Integrations and API access
- Email support
Scale
For teams that depend on this in production.
- Everything in Pro
- SSO and SCIM
- Audit log and data residency
- 99.9% uptime SLA
- Dedicated support channel
Prices in USD. Cancel any time from the dashboard — no email, no retention call.
Questions people actually ask
Do I need to talk to anyone to try this?
No. The free PublicACP tool runs without an account, a card or a call. That is the point of it.
What does it cost?
Pricing is published in full on this page.
Who is this actually for?
Security teams building allowlists, developers choosing which agent services to trust, and enterprises writing procurement policy for agent…
What problem does it solve?
Connecting an agent to a third-party service grants it credentials and the ability to act.
Can I get my data out?
Yes. Everything you put in can be exported as CSV or JSON at any time, and deleting your account deletes your data.
Why should I trust the result?
Trust registries become standards by being early, evidence-based and incorruptible, and refusing paid score adjustment is the expensive commitment that makes the whole thing worth citing.
Filter the way you actually choose
Free and public forever, with the full methodology published so scores can be disputed on the evidence rather than treated as opinion. Runs in your browser. No account, no card, no call.
Open the free toolIt runs in your browser. PublicACP never sees your inputs.