Thruact
Name the job, not the vendor. Routes a provider, fails over, catalog off the tool list.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'thruact_wallet' description lacks action verbin thruact_wallet
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": {
"thruact": {
"url": "https://thruact.com/mcp"
}
}
}Remote endpoints
https://thruact.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟢thruact_discover(limit, query)
Find capabilities for a job, with prices and measured reliability. Search first, execute second.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"description": "Max candidates",
"type": "integer"
},
"query": {
"description": "Natural language job",
"type": "string"
}
},
"required": [
"query"
]
}⚪thruact_act(capability, hedge, input, max_cost_usd, prefer)
Run a capability. Routes across providers and fails over automatically on provider faults. The reply's `route` says which providers were considered, what each scored, and why any were not used — including ones dropped for a missing credential.
Input Schema
{
"type": "object",
"properties": {
"capability": {
"type": "string"
},
"hedge": {
"description": "Race a backup provider if the first is slower than usual. Cuts tail latency; you are charged for one answer.",
"type": "boolean"
},
"input": {
"type": "object"
},
"max_cost_usd": {
"description": "Ceiling for this call. Narrows which providers may be used rather than refusing outright; if nothing fits, the error names the cheapest price that would.",
"type": "number"
},
"prefer": {
"description": "What to optimise for among the providers that fit the ceiling.",
"enum": [
"cheapest",
"fastest"
],
"type": "string"
}
},
"required": [
"capability"
]
}⚪thruact_compare(capability, input, providers)
Ask every provider behind a capability the same question at once and report where their answers differ. Use it when the answer matters enough to want it corroborated. Costs more than act: every provider called is paid.
Input Schema
{
"type": "object",
"properties": {
"capability": {
"type": "string"
},
"input": {
"type": "object"
},
"providers": {
"description": "How many providers to ask. Omit for all of them.",
"type": "integer"
}
},
"required": [
"capability"
]
}⚪thruact_call(params, tool)
Run one specific tool by id. No failover.
Input Schema
{
"type": "object",
"properties": {
"params": {
"type": "object"
},
"tool": {
"type": "string"
}
},
"required": [
"tool"
]
}⚪thruact_wallet
Prepaid balance and recent charges.
Input Schema
{
"type": "object",
"properties": {}
}⚪thruact_iq(capability)
Measured reliability per tool over the last 7 days.
Input Schema
{
"type": "object",
"properties": {
"capability": {
"type": "string"
}
}
}🟡thruact_proxy(body, method, path, vendor)
Send an authenticated request to a third-party vendor the workspace has connected. The stored API key is injected server-side — you never see it. Give the vendor id from the directory (e.g. openai, sendgrid), an HTTP method, and a path on that vendor's own API. Use it to act through a connected vendor that is not a Thruact capability. Metered per call.
Input Schema
{
"type": "object",
"properties": {
"body": {
"description": "JSON request body for POST/PUT/PATCH",
"type": "object"
},
"method": {
"enum": [
"GET",
"POST",
"PUT",
"PATCH",
"DELETE"
],
"type": "string"
},
"path": {
"description": "Path on the vendor's API, e.g. /v1/models",
"type": "string"
},
"vendor": {
"description": "Vendor id from the directory",
"type": "string"
}
},
"required": [
"vendor",
"path"
]
}Community
Evidence