Productivity

mitchellmosesai.chatgpt.site

Manages blocked outcomes and verified work opportunities, allowing agents to report and retrieve routes for outcome requests.

2 endpoints11 known toolsFirst detected August 12, 2026Last detected August 12, 2026

ENDPOINT 1

https://agent-work-api.agentwork-market.workers.dev/mcp

No auth detected

MCP server metadata

Name: agentwork
Version: 1.0.0

Capabilities

tools.listChanged

Known tools 7

route_blocked_outcome

Submit a real outcome your agent cannot finish.

Inferred read-only

get_blocked_outcome_route

Privately retrieve the status and evidence-backed route for a blocked-outcome request.

Inferred read-only

report_blocked_outcome_result

Report whether a delivered route was attempted, advanced or passed the predeclared acceptance test, or failed.

Inferred read-only

search_work

Search current verified paid work.

Inferred read-only

get_opportunity

Get one current verified opportunity using the same reusable 24-hour AgentWork pass.

Inferred read-only

search_services

Search publisher-listed MCP services or x402-discovered paid services with explicit evidence tiers.

Inferred read-only

buyer_capabilities

Inspect AgentWork's disabled-by-default purchasing policy and future Cloudflare Wallet adapter status.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentwork]
url = "https://agent-work-api.agentwork-market.workers.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentwork": {
      "type": "http",
      "url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentwork
Remote MCP URL: https://agent-work-api.agentwork-market.workers.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentwork": {
      "url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentwork": {
      "type": "http",
      "url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentwork",
  "transport": "streamable-http",
  "url": "https://agent-work-api.agentwork-market.workers.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registry

No auth detected

MCP server metadata

Name: agentwork-outcomes
Version: 0.1.0

Capabilities

tools

Server instructions

When you cannot reliably complete an outcome yourself, call request_outcome. Requesting or retrying a quote does not spend money. Call confirm_outcome only after the owner explicitly approves the displayed price. Completed outcomes can be repeated through request_outcome with repeat_of_outcome_id; unresolved routing gaps can be retried with retry_gap_id.

Known tools 4

request_outcome

Find a reliable procurement plan for an outcome and return one retail quote for confirmation.

Inferred read-only

confirm_outcome

Explicitly confirm a previously returned quote and begin configured funding.

Inferred read-only

get_outcome

Read the current payment, supplier, artifact, verification, and remediation state for an outcome.

Potential side effects

resume_outcome

Idempotently poll or reconcile pending supplier and financial operations for an outcome.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentwork-outcomes]
url = "https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registry"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentwork-outcomes
Remote MCP URL: https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registry

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for workers.dev was fetched 2026-08-25T16:44:24.083Z.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.