Toolhouse
Toolhouse is a Backend-as-a-Service platform for building, deploying, and managing "AI workers" (Toolhouse's current product noun, used interchangeably with "AI agents"). The homepage frames the value proposition as "Turn your AI chats into affordable and reliable AI workers that do work while you're busy," and the docs define a worker as "a system that carries out a task with three components: a trigger, a process that may include specialized skills, and tools or systems it can connect to." Builders describe a task in plain language in the Agent Editor and ship a worker to production; developers can do the same programmatically via SDKs. Every worker is automatically wired into Toolhouse's pre-integrated capabilities, including web and social media search, scraping, Toolhouse RAG, persistent memory, the Virtual Computer code-execution sandbox, image generation/editing and vision, document parsing, file download, and MCP Discovery for connecting to thousands of MCP servers at runtime. The platform exposes a Workers API (agents.toolhouse.ai) for invoking deployed workers over REST with text and NDJSON streaming and stateful conversation continuity (X-Toolhouse-Run-ID), a Platform API for full worker and run lifecycle management, scheduling (10-minute minimum cadence), metrics, monetization, and integrations, plus no-code workflow integration through Zapier and Toolhouse n8n Nodes. Toolhouse runs on a broad model substrate including OpenAI, Anthropic, Together AI, Groq, and NVIDIA model offerings. The current public pricing surface is Business ($500/mo, 25,000 credits, 50 workers), Business Max ($1,200/mo, 80,000 credits, 500 workers), and custom Enterprise — all plans include "free unlimited tokens" and a 14-day free trial. Toolhouse reports 7,000+ teams on the platform and 40+ integrations and is backed by NextGenerationEU funding.
Solid contracts, transparent operations, and an easy start — typically complete on four or five facets with one clear soft spot.
API Evangelist profiles Toolhouse the way a machine reads it — 84 machine-readable artifacts across 8 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Toolhouse scores 64.4/100 (strong), with a separate agent-readiness read of 60/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Toolhouse
Each block below is one kind of artifact we hold for Toolhouse. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 8
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Toolhouse Workers API
The Toolhouse Workers API (historically the "Agents API") enables HTTP execution of any deployed Toolhouse worker. Workers defined via the Agent Editor or as code are reachable ...
Toolhouse Agent Runs API
The Agent Runs API from Toolhouse — 4 operation(s) for agent runs.
Toolhouse API Keys API
The API Keys API from Toolhouse — 3 operation(s) for api keys.
Toolhouse Backoffice API
The Backoffice API from Toolhouse — 15 operation(s) for backoffice.
Toolhouse Logs API
The Logs API from Toolhouse — 2 operation(s) for logs.
Toolhouse Metrics API
The Metrics API from Toolhouse — 4 operation(s) for metrics.
Toolhouse SDK API API
The SDK API API from Toolhouse — 20 operation(s) for sdk api.
Toolhouse User API API
The User API API from Toolhouse — 58 operation(s) for user api.
Scroll within the panel for all 8 ·
MCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
MCP Server
MCP SERVERRate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Toolhouse Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Toolhouse Finops
FINOPSFeatures 25
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
AI Worker Deployment from a Prompt (Agent Editor)
Agent Studio (v2)
Workers API (REST + Streaming + NDJSON)
Stateful Conversational Memory (X-Toolhouse-Run-ID)
Attachments via URL or Base64 (10 MB max)
MCP Discovery
MCP Server Integration
Toolhouse RAG
Skills and Knowledge (Templates, Guidelines, Reference)
Virtual Computer (Python Sandbox)
Browser Automation
Web and Social Media Search
Image Generation, Editing, and Vision
Document Parser
File Download
Memory
Scheduled Worker Runs (cron, 10-minute floor)
Worker Email Inbox
Worker Run Logs (incl. MCP Server Logs)
Worker Run Metrics And Volume Reporting
API Key Management
Organizations
Agent Subscriptions, Monetization, and Transfer
Streaming Responses (Text + NDJSON)
Free Unlimited Tokens On All Plans
Scroll within the panel for all 25 ·
Semantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Toolhouse Context
JSON-LDSpectral Rules 2
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Toolhouse API Rules
SPECTRALToolhouse API Rules
SPECTRALJSON Schema 1
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
Toolhouse Agent
JSON SCHEMAJSON Structure 1
JSON Structure captures the data shapes in a form built for tooling — a complement to JSON Schema that keeps the model machine-legible.
JSON Structure definitions describing this provider's data shapes.
Toolhouse Agent Structure
JSON STRUCTUREExamples 2
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Security Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 11
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
AI Worker Backend-as-a-Service
Deal Analysis and Market Research Automation
Document Processing (Policy Abstraction, Summarization, Query)
Knowledge Assistants For Policy and Business Data
Lead Generation and Outbound Automation (SMS, Cold Calling, Inbound)
Marketing and Content Creation (Listings, Copy, Image Generation)
Automated Worker Scheduling
Tool-Augmented LLM Pipelines
Agent Studio Chat
MCP Client Integration
Production Worker Deployment
Scroll within the panel for all 11 ·
Integrations 27
Pre-built integrations with other platforms tell you where this provider already fits in a stack.
Pre-built integrations with other platforms and tools.
OpenAI
Anthropic Claude
Together AI
Groq
NVIDIA (Llama 3.1 Nemotron 70B)
Tavily (Official Partner)
Vercel AI SDK
LlamaIndex
n8n (Toolhouse n8n Nodes)
Zapier
Supabase
Lovable
GitHub
GitLab
Bitbucket
Stripe
Square
QuickBooks
Salesforce
HubSpot
Microsoft Dynamics 365
Google Workspace (Sheets, Docs, Drive)
Microsoft Teams
Slack
Discord
Notion
MCP Clients (via MCP Server and MCP Discovery)
Scroll within the panel for all 27 ·
Resources
Every other property we hold for Toolhouse — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 1
Portal, sign-up, and the first successful call
Documentation 3
Reference material describing how the API behaves
Agent Surfaces 3
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 4
Pagination, idempotency, versioning, errors, and events
Build 9
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 9 ·
Access & Security 3
Authentication, authorization, and security posture
Learn 1
Tutorials, courses, talks, and written guidance
Operate 5
Status, limits, changes, and where to get help
Commercial 5
Pricing, plans, and the legal terms of use
Company 5
The organization behind the API
Other 6
Properties that don't map to a standard resource type
← All providers · Data indexed from github.com/api-evangelist/toolhouse · machine-readable index on apis.io