Skip to content
DCL Trust Oracle logo

DCL Trust Oracle

Records hashes of each agent decision in a linked chain, so any altered entry fails verification.

At a glanceswept 2026-10-12

29 installs/mo

Emerging

For
developers and teams running AI agents who need to verify what agents decided
Price
Price not read
Activity
Actively maintainedrelease 2 days ago
Company
Domain since 2026domain registered
Runs as
SDK
What people do with it
  • verify an agent's decision chain for tampering
  • seal agent decisions into a tamper-evident hash chain
  • screen agent outputs for jailbreaks, secrets and PII
The companyeach fact with its source · read 2026-10-13
  • Domain since2026domain registered
How a program reaches itfound, not claimed · read 2026-10-13
  • MCP servercom.fronesislabs/dcl-trust-oracleverified in the MCP registry
  • Stateanswers, 18 toolschecked 2026-10-13
  • Address to connectmcp.fronesislabs.com/mcp

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Agentsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Agents tools →

Questions this page answers
  • What is DCL Trust Oracle?

    Records hashes of each agent decision in a linked chain, so any altered entry fails verification. It is listed in the Atlas under Agents.

  • Who is DCL Trust Oracle for?

    developers and teams running AI agents who need to verify what agents decided

  • Do people use DCL Trust Oracle?

    Emerging: 29 installs/mo (npm).

  • Is DCL Trust Oracle still maintained?

    Actively maintained: release 2 days ago.

  • What are alternatives to DCL Trust Oracle?

    In Agents, by use: claude-devtools, Aqta, Tandem, Satcove, ClawBuddy, Chloros.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.