DidWork MCP server

by didwork.sh·sh.didwork/didwork·v0.0.10

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

B80/100grade B

What users say

No reviews yet

Safety scan

B80/100

Adoption

Growing

1 stars96 downloads/wk

Reviews

Nobody has reviewed DidWork yet.

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

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_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. Send a claim
did_watch
Continuously re-verify a claim on an interval (e.g. '10m', '1h').
did_watches
List active watches with their last verdicts.

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings

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
Maintenancelast push 3 days ago15/15
Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10

Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

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

Is DidWork MCP server safe?: Mostly: it is graded B (80/100). Read the DidWork safety report
How do I install DidWork?: It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor 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 4 days ago (2026-09-17). The latest release is v0.0.10.
What can I use instead of DidWork?: Servers from other publishers that do the same job: Watch Skill MCP server, agent-device MCP server and Mockserver MCP server. Compare all DidWork alternatives.

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.
not reviewed
Growing
B
agent-device
MCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps
not reviewed
Widely used
A
Mockserver
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
not reviewed
Established
A
Skillsmith
Share agent skills across your team, scan them for risk, and track what's actually used.
not reviewed
Established
B
HOL Guard
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
not reviewed
Established
A

Local package. It runs on your machine, not through the gateway.

DIDWORK_API_KEYsecretDidWork API key, free at https://didwork.sh/console. Optional: the server falls back to the ~/.didwork/api_key file (or DIDWORK_API_KEY_FILE); with no key at all it runs keyless and only http.ok claims verify.
DIDWORK_BASE_URLOverride the DidWork API base URL (defaults to the hosted API)

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/didwork.svg)](https://mcp.market/server/didwork)