DidWork as an MCP server: gives any MCP-capable agent — Claude Code, Claude Desktop, Cursor, or your own — a did_verify tool, so the agent gates its next action on independently gathered evidence instead of grading its own work.

Agent acts → did_verify(claim) → VERIFIED / FAILED / UNKNOWN → agent proceeds or escalates

Setup

You need a DidWork API key — free at didwork.sh/console.

Claude Code

claude mcp add didwork -e DIDWORK_API_KEY=dk_your_key -- npx -y @didwork/mcp

Cursor (~/.cursor/mcp.json) or Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "didwork": {
      "command": "npx",
      "args": ["-y", "@didwork/mcp"],
      "env": { "DIDWORK_API_KEY": "dk_your_key" }
    }
  }
}

Tools

Tool	Does
`did_verify`	Verify a claim now — returns the verdict with evidence attached
`did_get`	Fetch a verification by id (poll async verifications)
`did_list`	Recent verifications for this key, evidence included
`did_watch`	Re-verify a claim on an interval; webhook on verdict transitions
`did_watches`	List active watches and their last verdicts
`did_unwatch`	Stop a watch
`did_usage`	Verifications performed, by month

Claim types

stripe.refund, stripe.payment_succeeded, stripe.subscription_active, stripe.subscription_cancelled, stripe.invoice_paid, github.pr_merged, github.workflow_passed, github.issue_closed, github.release_published, github.commit_in_branch, github.file_exists, gitlab.mr_merged, gitlab.pipeline_passed, gitlab.issue_closed, sentry.issue_resolved, jira.issue_done, linear.issue_completed, slack.message_posted, email.delivered, and http.ok (any public URL — no provider connection needed).

Field reference: didwork.sh/docs#claims. Providers connect once, read-only, at didwork.sh/console.

Prompting the agent

A line like this in your agent's instructions makes the tool bite:

After any consequential action (refund, deploy, ticket close, message send), call did_verify with the matching claim before reporting success. Proceed only on verified. Treat failed and unknown as stop-and-escalate.