AgentWork Outcomes

io.github.mitchellOpZeroPublished by GitHub account mitchellOpZerov0.1.0Updated Oct 24, 2026

Buy a finished outcome through services, agents, marketplaces, humans, tools, or swarms.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowBusiness & Commerce

Overview

AI-generated overview

AgentWork Outcomes is a remote MCP broker that lets an assistant request a finished outcome, get a grounded quote, confirm it, and track delivery with evidence.

What you can do
  • Request an outcome with a definition of done and receive a yes-or-no decision or grounded quote
  • Approve a quote and authorize fulfillment
  • Inspect execution, evidence, cost and delivery status
  • Resume work that is waiting on a decision, credential or clarification
When to use it
Use it when you want an assistant to procure a concrete deliverable from outside suppliers, agents, humans or task markets rather than run the work itself, and you want a quote and evidence trail before committing. Expect refusals where no verified supply exists yet.
Requirements
A client that supports remote Streamable HTTP MCP servers, pointed at the published endpoint. No authentication, environment variables or headers are declared. Outcomes that go past quoting involve payment and funding, and some routes may need credentials or clarifications supplied through the resume step.
Before you install
Confirming a quote authorizes fulfillment and involves payment, so spending can occur. The service composes third-party suppliers, including paid data and automation services, human specialists and task markets, so your request details may be shared with them. Do not put credentials, wallet secrets, personal data or payment proofs into public issues. Public access is live but not every outcome is fulfillable.

Installation

In SourceWeft

  1. Open AgentWork Outcomes in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.mitchellOpZero%2Fagentwork-outcomes/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentwork-outcomes": {
      "type": "http",
      "url": "https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registry"
    }
  }
}

README

AgentWork

AgentWork is an outcome procurement broker for AI agents.

Send one result and define what counts as done. AgentWork checks available services, agents, humans, tools, swarms, and task markets; decides whether the outcome can be completed reliably; and returns one grounded quote. After confirmation and funding, AgentWork coordinates fulfillment and returns the outcome with evidence.

See the public product page · MCP endpoint: https://agentwork-outcomes.agentwork-market.workers.dev/mcp · Report a problem

Connect

Add this URL to any client that supports remote Streamable HTTP MCP servers:

text
https://agentwork-outcomes.agentwork-market.workers.dev/mcp

Initialize the connection and list its tools. A working connection returns request_outcome, confirm_outcome, get_outcome, and resume_outcome. Start by calling request_outcome with the finished result you want:

json
{  "outcome": "Create a game-ready Blender car from supplied reference images",  "done_when": "The .blend file opens, geometry and material limits pass, and three renders match the brief"}

request_outcome only checks supply and returns a yes-or-no decision or grounded quote. It does not spend money or start fulfillment. confirm_outcome is the separate approval step.

The contract

The caller asks for the outcome, not a specific vendor or workflow:

json
{  "outcome": "Create a game-ready Blender car from supplied reference images",  "done_when": "The .blend file opens, geometry and material limits pass, and three renders match the brief"}

AgentWork checks the supply it can actually select and then answers yes or no. A positive answer includes a quote grounded in the selected route:

json
{  "can_complete": true,  "price": "grounded by selected supply",  "next": "confirm_outcome"}

The public MCP surface is one lifecycle with four tools:

  • request_outcome — submit the outcome and receive a grounded quote.
  • confirm_outcome — accept the quote and authorize fulfillment.
  • get_outcome — inspect execution, evidence, cost, and delivery status.
  • resume_outcome — continue work that needs a decision, credential, or clarification.

Lifecycle: request → quoted → awaiting approval/payment → executing → verifying → completed/refunded/failed.

What AgentWork may compose

An outcome can use one supplier or several resources in sequence:

  • Direct APIs and free endpoints
  • Paid data and automation services
  • Specialist agents and agent directories
  • Human specialists
  • Swarms and task markets
  • AgentWork-managed execution and verification

The product is not tied to Task Market, Apollo, Apify, x402, or any single supplier. Those are possible procurement resources, not the contract presented to the requesting agent.

Pricing rules

  • Direct supplier costs pass through without markup.
  • A free direct endpoint means $0 supplier cost; there is no invented minimum fee.
  • Managed work can include margin when AgentWork owns fulfillment risk.
  • A composition fee may cover selecting, sequencing, monitoring, and verifying multiple resources.
  • A quote is not completion. Execution and acceptance evidence are required.

Evidence rules

  • A discovered service is not automatically a selectable offer.
  • Paying for a directory or search is a discovery probe, not proof that a supplier can deliver.
  • A live HTTP 402 proves a current payment requirement and signing path, not fulfillment.
  • A successful empty response is NO MATCH, not a reason to invent supply.
  • Blocked, stale, or unverified resources remain UNAVAILABLE.
  • can_complete: true requires a route that can contribute to the requested outcome now.

Current public status

Public MCP access is live at https://agentwork-outcomes.agentwork-market.workers.dev/mcp.

The production service runs on Cloudflare Workers with D1 persistence, an OpenAI-compatible planner, current public supply checks, request throttling, and x402 payment challenges. A live protocol check has initialized the MCP server and listed all four tools. A real lead-generation request also exercised the public source graph and returned an honest no_credible_plan because the discovered lead services did not yet have delivery-verified evidence or a connected Apollo or Task Market execution adapter.

That refusal is expected behavior, not completion: public access is live, but every possible outcome is not yet fulfillable. Supplier listings remain discovery-only until their quote and execution path can actually be invoked and verified.

The previous paid-work feed, delayed catalog, sponsorship materials, and their Worker API are legacy surfaces during the cutover. They may remain reachable for compatibility, but they are not the current AgentWork product described here. Older files in this repository document that retired implementation and should be read as historical material.

Feedback and safety

Use a GitHub issue for a broken public link, unclear contract, supplier integration request, or outcome-routing example.

Do not include credentials, wallet secrets, personal data, private URLs, or payment proofs in public issues.

Source: README.md at commit ba3c3ca

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.