AgentWork Outcomes is an MCP server published by io.github.mitchellOpZero, hosted at agentwork-outcomes.agentwork-market.workers.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including request_outcome, confirm_outcome, get_outcome, resume_outcome.
Buy a finished outcome through services, agents, marketplaces, humans, tools, or swarms.
3 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Find a reliable procurement plan for an outcome and return one retail quote for confirmation. This does not spend, post, purchase, or invoke anything.
| Parameter | Type | Description |
|---|---|---|
| context | object | Optional non-secret context needed to plan the outcome. |
| outcome | string | The complete outcome the caller wants. |
| deadline | string | Optional delivery deadline. |
| done_when | string | Optional observable completion criteria. |
| retry_gap_id | string | Retry a previously recorded routing or scoping gap with fresh supply checks. |
| authority_scopes | array | Explicit non-financial authority granted for this outcome. Quote confirmation grants spend only. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| max_spend_micros | integer | Optional maximum retail spend in USDC micros. Zero permits only free routes. |
| repeat_of_outcome_id | string | Reuse a verified route where compatible. Supply a fresh outcome, done_when, inputs, and authority; previous values are never inherited. |
{
"name": "request_outcome",
"title": "Request an outcome",
"description": "Find a reliable procurement plan for an outcome and return one retail quote for confirmation. This does not spend, post, purchase, or invoke anything.",
"inputSchema": {
"type": "object",
"oneOf": [
{
"not": {
"anyOf": [
{
"required": [
"retry_gap_id"
]
},
{
"required": [
"repeat_of_outcome_id"
]
}
]
},
"required": [
"outcome"
]
},
{
"not": {
"anyOf": [
{
"required": [
"outcome"
]
},
{
"required": [
"repeat_of_outcome_id"
]
}
]
},
"required": [
"retry_gap_id"
]
},
{
"not": {
"required": [
"retry_gap_id"
]
},
"required": [
"repeat_of_outcome_id"
]
}
],
"properties": {
"context": {
"type": "object",
"description": "Optional non-secret context needed to plan the outcome."
},
"outcome": {
"type": "string",
"description": "The complete outcome the caller wants."
},
"deadline": {
"type": "string",
"format": "date-time",
"description": "Optional delivery deadline."
},
"done_when": {
"type": "string",
"description": "Optional observable completion criteria."
},
"retry_gap_id": {
"type": "string",
"description": "Retry a previously recorded routing or scoping gap with fresh supply checks."
},
"authority_scopes": {
"type": "array",
"items": {
"enum": [
"read_public_data",
"contact_external_party",
"represent_requester",
"create_account",
"create_or_use_wallet",
"publish",
"use_private_data"
],
"type": "string"
},
"description": "Explicit non-financial authority granted for this outcome. Quote confirmation grants spend only.",
"uniqueItems": true
},
"max_spend_micros": {
"type": "integer",
"minimum": 0,
"description": "Optional maximum retail spend in USDC micros. Zero permits only free routes."
},
"repeat_of_outcome_id": {
"type": "string",
"description": "Reuse a verified route where compatible. Supply a fresh outcome, done_when, inputs, and authority; previous values are never inherited."
}
},
"additionalProperties": false
}
}Explicitly confirm a previously returned quote and begin configured funding. This may cause a financial action when funding is enabled.
| Parameter | Type | Description |
|---|---|---|
| quote_id * | string |
{
"name": "confirm_outcome",
"title": "Confirm an outcome quote",
"description": "Explicitly confirm a previously returned quote and begin configured funding. This may cause a financial action when funding is enabled.",
"inputSchema": {
"type": "object",
"required": [
"quote_id"
],
"properties": {
"quote_id": {
"type": "string"
}
},
"additionalProperties": false
}
}Read the current payment, supplier, artifact, verification, and remediation state for an outcome.
| Parameter | Type | Description |
|---|---|---|
| outcome_id * | string |
{
"name": "get_outcome",
"title": "Get an outcome",
"description": "Read the current payment, supplier, artifact, verification, and remediation state for an outcome.",
"inputSchema": {
"type": "object",
"required": [
"outcome_id"
],
"properties": {
"outcome_id": {
"type": "string"
}
},
"additionalProperties": false
}
}Idempotently poll or reconcile pending supplier and financial operations for an outcome.
| Parameter | Type | Description |
|---|---|---|
| outcome_id * | string |
{
"name": "resume_outcome",
"title": "Resume an outcome",
"description": "Idempotently poll or reconcile pending supplier and financial operations for an outcome.",
"inputSchema": {
"type": "object",
"required": [
"outcome_id"
],
"properties": {
"outcome_id": {
"type": "string"
}
},
"additionalProperties": false
}
}When you cannot reliably complete an outcome yourself, call request_outcome with the complete task, observable done_when, current inputs, and explicitly granted authority. Requesting or retrying a quote does not spend money. Call confirm_outcome only after the owner explicitly approves the new displayed price. To reuse a verified route, include repeat_of_outcome_id together with a fresh outcome, done_when, context, and authority; previous inputs and permissions are never inherited. Unresolved routing gaps can be retried with retry_gap_id.
Names, descriptions and schemas were written by the server and are shown as data.