MCP.Market

DidWork MCP server

by didwork.sh·sh.didwork/didwork·v0.1.1·1 stars
No reviews yet

Verify that an agent's claimed outcome actually happened, using independently gathered evidence

C58/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C58/100

full report

Adoption
Growing

1 stars82 downloads/wk

Reviews

Write one

Nobody has reviewed DidWork yet.

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

DidWork tools (10, 1 write)

write = sends, deletes, buys or posts

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

  • did_get

    Fetch a verification by id (poll a pending async verification).

  • did_get_runwrite action

    Read an outcome run by id. Running, failed and unknown are not completed success.

  • did_inspect_tool

    Capability Trust: before calling an agent tool with real-world consequences (money,

  • did_list

    Recent verifications for this API key — the developer log, evidence included.

  • did_unwatch

    Stop a watch by id.

  • did_usage

    Verifications performed, by month.

  • did_verify

    Independently verify that an intended outcome is actually true.

  • did_verify_contract

    Verify a reviewed version 2 outcome contract. Pass the requirements unchanged; never remove or weaken requirements to obtain a pass. The caller must load the contract from the trusted source. DidWork records caller-supplied provenance, independently gathers claim evidence and returns a run. Reuse the same idempotency_key after an interrupted request. A verified run covers only its required checks.

  • did_watch

    Continuously re-verify a claim on an interval (e.g. '10m', '1h').

  • did_watches

    List active watches with their last verdicts.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

1 low
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenanceno repository listed3/15
  • Maintainer identityverified namespace with website, no repo4/10

Findings (1)

  • lowNo source repository listedmaint.no-repo
Overall 58/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How DidWork compares

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

Safety score
58/100
higher than 15% of 4,461 AI and agents servers
Tools
10
the typical AI and agents server has 6
Tools that change things
10%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 50% of 2,713 AI and agents servers
Downloads a week
82
more than 57% of 1,554 AI and agents servers with a package

What its tools let an agent do: 9 read · 1 change

Release history: 3 versions in the registry since 2026-09-05, latest 2026-09-23, typically one every 15 days.

Install DidWork in Claude Code, Cursor or VS Code

Runs npx -y @didwork/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add didwork -- npx -y @didwork/mcp
Add to Cursor

Grade history

  • 2026-10-16downgradeB → Cscore 58: No source repository listed

DidWork: common questions

Is DidWork MCP server safe?
With care: it is graded C, so read the findings first (58/100). Read the DidWork safety report
How do I install DidWork?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does DidWork need an API key?
Yes. The registry entry asks for DIDWORK_API_KEY.
Is DidWork maintained?
The last commit was 49 days ago (2026-09-17). The latest release is v0.1.1.
What can I use instead of DidWork?
Servers from other publishers that do the same job: Watch Skill MCP server, HOL Guard MCP server and OpenWorkProof MCP server.
How does DidWork compare with other AI and agents MCP servers?
safety score 58/100 (higher than 15% of 4,461 AI and agents servers); tools 10 (the typical AI and agents server has 6); tools that change things 10% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to DidWork

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

  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • Mnemoverse Memory
    Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
    A