AgentWork Outcomes
Buy a finished outcome through services, agents, marketplaces, humans, tools, or swarms.
Should I use this
Quality & Safety
Findings (1)
- LOWin resume_outcome
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"agentwork-outcomes": {
"url": "https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registry"
}
}
}Remote endpoints
https://agentwork-outcomes.agentwork-market.workers.dev/mcp?source=mcp-registrystreamable-httpWhat it can do
Tool inventory
Tools (4)
🟢request_outcome(outcome, retry_gap_id, repeat_of_outcome_id, done_when, context, ...)
Find a reliable procurement plan for an outcome and return one retail quote for confirmation. This does not spend, post, purchase, or invoke anything.
Input Schema
{
"type": "object",
"properties": {
"outcome": {
"type": "string",
"description": "The complete outcome the caller wants."
},
"retry_gap_id": {
"type": "string",
"description": "Retry a previously recorded routing or scoping gap with fresh supply checks."
},
"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."
},
"done_when": {
"type": "string",
"description": "Optional observable completion criteria."
},
"context": {
"type": "object",
"description": "Optional non-secret context needed to plan the outcome."
},
"max_spend_micros": {
"type": "integer",
"minimum": 0,
"description": "Optional maximum retail spend in USDC micros. Zero permits only free routes."
},
"authority_scopes": {
"type": "array",
"items": {
"type": "string",
"enum": [
"read_public_data",
"contact_external_party",
"represent_requester",
"create_account",
"create_or_use_wallet",
"publish",
"use_private_data"
]
},
"uniqueItems": true,
"description": "Explicit non-financial authority granted for this outcome. Quote confirmation grants spend only."
},
"deadline": {
"type": "string",
"format": "date-time",
"description": "Optional delivery deadline."
}
},
"oneOf": [
{
"required": [
"outcome"
],
"not": {
"anyOf": [
{
"required": [
"retry_gap_id"
]
},
{
"required": [
"repeat_of_outcome_id"
]
}
]
}
},
{
"required": [
"retry_gap_id"
],
"not": {
"anyOf": [
{
"required": [
"outcome"
]
},
{
"required": [
"repeat_of_outcome_id"
]
}
]
}
},
{
"required": [
"repeat_of_outcome_id"
],
"not": {
"required": [
"retry_gap_id"
]
}
}
],
"additionalProperties": false
}⚪confirm_outcome(quote_id)
Explicitly confirm a previously returned quote and begin configured funding. This may cause a financial action when funding is enabled.
Input Schema
{
"type": "object",
"properties": {
"quote_id": {
"type": "string"
}
},
"required": [
"quote_id"
],
"additionalProperties": false
}🟢get_outcome(outcome_id)
Read the current payment, supplier, artifact, verification, and remediation state for an outcome.
Input Schema
{
"type": "object",
"properties": {
"outcome_id": {
"type": "string"
}
},
"required": [
"outcome_id"
],
"additionalProperties": false
}⚪resume_outcome(outcome_id)
Idempotently poll or reconcile pending supplier and financial operations for an outcome.
Input Schema
{
"type": "object",
"properties": {
"outcome_id": {
"type": "string"
}
},
"required": [
"outcome_id"
],
"additionalProperties": false
}Community
Evidence