mcpField
D

DidWork

Local
didwork.shAI & Agents
Visit website

About DidWork

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "sh-didwork-didwork": {
      "command": "npx",
      "args": [
        "-y",
        "@didwork/mcp"
      ],
      "env": {
        "DIDWORK_API_KEY": "<DIDWORK_API_KEY>",
        "DIDWORK_BASE_URL": "<DIDWORK_BASE_URL>"
      }
    }
  }
}
Run commandnpx -y @didwork/mcp
Environment variables to set
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)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@didwork/mcp0.1.1

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
typestringYesClaim type, e.g. 'stripe.refund' or 'http.ok'
waitbooleanNofalse = return a pending verification immediately and poll with did_get
toolsarrayNoThe tools that performed the work, as profiles from did_inspect_tool or { name, capabilities } records. Recorded on the receipt as caller-reported context (what the tools could affect); the verdict does not depend on it.
accountstringNoWhich connected account to verify against, by the label the user gave it in the console (e.g. 'acme'). Omit to try every account connected for the provider.
subjectstringNoOptional caller-side reference id
expectedobjectYesThe claim's expected fields. For github.commit_in_branch use { repository: 'owner/repo', branch: 'main', commit: 'full-sha' }; for stripe.refund use { payment: 'pi_123', amount: 4999 }.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.