MCP.Market

DOS — the trust substrate for agent fleets MCP server

by anthony-chaudhary·io.github.anthony-chaudhary/dos-kernel·v0.30.0·20 stars
No reviews yet

Verify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.

B77/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Growing

20 stars95 downloads/wk

Reviews

Write one

Nobody has reviewed DOS — the trust substrate for agent fleets yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

DOS — the trust substrate for agent fleets tools (13)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • _readme_for
  • _tool
  • dos_answer

    Ask DOS "how do I X?" and get the canonical, sourced answer page.

  • dos_arbitrate
  • dos_check_reason

    Is `reason_class` a member of the closed refusal vocabulary?

  • dos_citation_resolve

    Does this cited case EXIST — and does the quote MATCH? — the legal-citation witness.

  • dos_commit_audit

    Does a commit's CLAIM match what its DIFF actually did? — author-neutral.

  • dos_doctor

    The machine-readable workspace report — paths, lanes, stamp grammar.

  • dos_recall

    Is this recalled memory still TRUE? — re-verify a memory at read time.

  • dos_refuse_reasons

    The closed structured-refusal vocabulary for this workspace.

  • dos_review

    Review the RESIDUAL, not the diff — where is a human's attention actually owed?

  • dos_status

    One folded, fail-closed status fact for a run — liveness · progress · region · resume.

  • dos_verify

    Did (plan, phase) actually ship? — the truth syscall.

Public scan report

scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it

2 medium
  • Code scan233 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 5 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumsubprocess with shell=Trueexec.shell-true
    dos_kernel-0.30.0/src/dos/drivers/llm_judge.py: … return None try: # shell=True so an operator can set a full `claude -…
  • mediumeval / new Function usedexec.eval
    dos_kernel-0.30.0/src/dos/intervention_eval.py: …d `arg_provenance` shipped a *detector* eval (precision/recall over minted-vs-resolved…
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How DOS — the trust substrate for agent fleets compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
77/100
higher than 50% of 4,460 AI and agents servers
Tools
13
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
20
more than 89% of 2,711 AI and agents servers
Downloads a week
95
more than 63% of 1,538 AI and agents servers with a package

What its tools let an agent do: 13 read

Install DOS — the trust substrate for agent fleets in Claude Code, Cursor or VS Code

claude mcp add dos-kernel -- uvx dos-kernel
Add to Cursor

What the publisher says

From the DOS — the trust substrate for agent fleets repository's README, as published. We do not edit it. Read it on GitHub

<!-- GENERATED FILE — do not edit README.md directly. The source of truth is docs/readme/ (one file per section, assembled in filename order). Edit the part, then run: python scripts/buildreadme.py tests/testreadme_assembly.py pins this file to the parts. -->

DOS — the Dispatch Operating System

### Catch your AI agents when they lie about what they shipped.

📊 See it run on real repos: the scoreboard

scores 15 popular AI-built repos (roborev, open-interpreter, crewAI, autogen, …)

— how much agents wrote, which ones, and whether each commit's claim is backed

by its own diff. Score yours: dos commit-audit --sweep --workspace . BASE..HEAD.

The whole pitch in one recording: the agent claims two features shipped; git backs one. dos verify answers from the commits, the lie exits 1, and a gate on that exit code refuses the false "done". Every line is the real CLI's verbatim output — scripts/buildcaughtlie_cast.py re-records it whenever the output changes.

Run a fleet of agents on one repo. The left loop just feels like progress; the right one you can steer. The only difference is a verdict DOS reads from the real world — here, git — never the agent's word.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

DOS — the trust substrate for agent fleets: common questions

Is DOS — the trust substrate for agent fleets MCP server safe?
Mostly: it is graded B (77/100). Read the DOS — the trust substrate for agent fleets safety report
How do I install DOS — the trust substrate for agent fleets?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does DOS — the trust substrate for agent fleets need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is DOS — the trust substrate for agent fleets maintained?
The last commit was 44 days ago (2026-09-20). The latest release is v0.30.0.
What can I use instead of DOS — the trust substrate for agent fleets?
Servers from other publishers that do the same job: Basic Memory MCP server, Agent-Native Plan MCP server and Watch Skill MCP server.
How does DOS — the trust substrate for agent fleets compare with other AI and agents MCP servers?
safety score 77/100 (higher than 50% of 4,460 AI and agents servers); tools 13 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to DOS — the trust substrate for agent fleets

Same job from other publishers: the closest match first, then the best rated.

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent-Native Plan
    Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Mockserver
    Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
    A