Category · Work & business apps
Workflow automation platforms with APIs for agents
Workflow builders an agent can trigger, inspect or build in, from no-code scenarios to code-first scripts and embedded integrations. Compared on connection setup, authorisation, action coverage, retries, logs and cost per completed run.
Capability keys automation.workflows · automation.apps · automation.embedded · automation.code · automation.webhooks · All tools
letme.dev/automation.workflows picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 21 | TemporalTemporal Technologies · Model platform | Human approval | BB | 77.2 | 3.6 (8) | n/a | n/a | $0.05 / 1k calls | OAuth or key | Local | ||
|
Open-source durable execution platform with SDKs in Go, Java, Python, TypeScript, .NET, PHP, Ruby and Rust, run yourself or on Temporal Cloud. Top strength Waits of any length with a timeout survive worker restarts and deploys Top weakness No reviewer inbox, notifications or routing, so the human side is all your code |
||||||||||||
| 46 | Trigger.devTrigger.dev · Model platform | Human approval | BB | 74.8 | 3.6 (8) | n/a | n/a | Freemium | OAuth or key | Hosted + local | ||
|
Open-source background jobs and durable tasks in TypeScript. Top strength Tokens complete from a backend, a pre-signed callback URL or the browser with a token scoped to one waitpoint Top weakness 10-minute default timeout on tokens |
||||||||||||
| 160 | InngestInngest · Model platform | Human approval | B | 66.3 | 2.5 (2) | n/a | n/a | $99 / mo | OAuth or key | Hosted | ||
|
Durable execution platform for TypeScript, Python and Go, with event-driven workflows and support for human approval. Top strength Waits are durable and cost nothing while suspended, with runs up to 30 days on Free and 366 on Business Top weakness No reviewer inbox, Slack app or email, so the human side is your code |
||||||||||||
| 167 | Pipedream API + MCPPipedream (Workday) · HTTP API | Workflows | B | 65.8 | 2.5 (2) | n/a | n/a | $150 / mo | OAuth or key | Hosted | ||
|
Code-first workflows in Node.js, Python, Go and Bash, plus Connect, an API and SDK that runs 10,000+ prebuilt actions across 3,000+ apps on behalf of your own users with managed OAuth. Top strength Managed OAuth per end user across 3,000+ apps, through API, SDK or MCP Top weakness Public changelog's last entry is 1 October 2025 |
||||||||||||
| 274 | Make API + MCPMake (Celonis) · HTTP API | Workflows | C | 58.9 | 2.5 (2) | n/a | n/a | $12 / mo | OAuth or key | Hosted | ||
|
REST API (v2) for scenarios, runs, connections, webhooks, data stores and teams, plus a hosted MCP server that runs on-demand scenarios as tools and, on paid plans, manages the account. Top strength Hosted MCP server with OAuth, and scenario run tools on the free plan Top weakness No published OpenAPI file and no official SDK |
||||||||||||
| 282 | Workato API + MCPWorkato · HTTP API | Workflows | C | 58.3 | 3.5 (2) | n/a | n/a | $75 / mo | OAuth or key | Hosted | ||
|
Enterprise integration platform for building automated workflows. Top strength API client tokens scoped by role and project, with legacy full-access keys removed on 14 October 2025 Top weakness No OpenAPI file and no official SDK on npm or PyPI |
||||||||||||
| 288 | Activepieces API + MCPActivepieces · HTTP API | Workflows | C | 57.8 | 3.0 (2) | n/a | n/a | $20 / mo | OAuth or key | Hosted | ||
|
Open-source flow builder with 760+ app integrations (pieces), run on Activepieces Cloud or self-hosted. Top strength MIT core, self-hostable, with the enterprise parts clearly separated Top weakness Docs say API keys come from the platform dashboard in Platform and Enterprise editions, while the pricing page lists the API on every plan |
||||||||||||
| 306 | Windmill API + MCPWindmill Labs · HTTP API | Workflows | C | 56.1 | 3.0 (2) | n/a | n/a | $20 / seat-mo | OAuth or key | Hosted | ||
|
Code-first engine for scripts, flows and internal apps in 20+ languages, written in Rust, on Windmill Cloud or self-hosted. Top strength Token scopes down to a single script path, with expiry Top weakness The default MCP URL puts the token in |
||||||||||||
| 312 | Tray.ai API + MCPTray.ai · HTTP API | Workflows | C | 55.6 | 2.5 (2) | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
Low-code integration platform with an embedded product for SaaS vendors. Top strength Call any connector operation directly with a per-end-user token, no workflow needed Top weakness No published prices and no self-serve plan |
||||||||||||
| 327 | Orkes Conductor Human tasksOrkes · Model platform | Human approval | C | 54.2 | 2.5 (2) | n/a | n/a | Paid | API key | Hosted + local | ||
|
Workflow orchestration platform, built on the open-source Conductor, with a Human task that pauses a workflow, assigns a form to a user or group and resumes with the submitted answer. Top strength Escalation chains with a time limit per assignee and a choice of leaving the task open or failing the workflow Top weakness No built-in Slack or email prompt, so alerts need a trigger policy and a second workflow |
||||||||||||
| 335 | n8n API + MCPn8n · HTTP API | Workflows | D | 53.3 | 2.5 (2) | n/a | n/a | Freemium | OAuth or key | Local | ||
|
Workflow builder you can run on n8n Cloud or self-host. Top strength OpenAPI 3.0 spec with 208 operations, and Markdown docs plus llms.txt Top weakness 24 critical advisories from December 2025 to May 2026, and CVE-2025-68613 was exploited in the wild |
||||||||||||
| 381 | Paragon ActionKit + MCPParagon · HTTP API | Workflows | D | 47.8 | 2.0 (2) | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
Embedded integration platform for SaaS products. Top strength Per-end-user RS256 JWT on every call, with a hosted Connect Portal for OAuth Top weakness No published prices and no self-serve paid plan |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
Indexed, not reviewed (29)
Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.
| Listing | Kind | What it does | Why it's here |
|---|---|---|---|
| Agency AI – Meta & Google Ads Automation agencyai.app | MCP server | Create, launch, and manage Meta + Google ads from Claude and ChatGPT. | vendor's own |
| agentfenster agentfenster.com | MCP server | Windows GUI automation on a hidden second desktop, driven from Claude Code over MCP. | vendor's own |
| AgentSEO www.agentseo.dev | MCP server | Live SEO workflow tools for Claude Code, Codex, and AI agents. | vendor's own |
| AutoMobile jasonpearson.dev | MCP server | Mobile device interaction automation via MCP | vendor's own, widely used |
| clarx.ai MCP server clarx.ai | MCP server | Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE. | vendor's own |
| CollHub collhub.com | MCP server | Documents, projects, comments, workflows and data sources of your CollHub instance, as tools. | vendor's own |
| contract-automation bitsbound.com | MCP server | AI contract automation with partner-level redlines, OOXML Track Changes, and risk analysis. | vendor's own |
| dex-data donnyautomation.com | MCP server | DEX market data, SEC EDGAR change oracles, LEI and US Treasury curve. 13 tools, x402 paid. | vendor's own |
| docs-mcp tandem.ac | MCP server | Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help. | vendor's own |
| dossier imboard.ai | MCP server | MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers | vendor's own |
| Easy Labs MCP Server itseasy.co | MCP server | Payments data, revenue workflows, and merchant-application guidance for AI agents, by Easy Labs. | vendor's own |
| Elasticflow elasticflow.app | MCP server | AI-native team workspace — tables, documents, workflow automation, live dashboards & analytics | vendor's own |
| Faldaro faldaro.com | MCP server | Forms, submissions, workflows and reports in Faldaro, exactly as privileged as your API key. | vendor's own |
| FlyDocs flydocs.ai | MCP server | Spec-driven development workflow: your agent works issues, sessions and the status lifecycle. | vendor's own |
| formio-uag form.io | MCP server | The Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io. | vendor's own |
| gitscrum.com MCP server gitscrum.com | MCP server | MCP server for GitScrum — manage tasks, sprints, time tracking, and client workflows via AI | vendor's own |
| Goodeye goodeye.dev | MCP server | Design, save, and run outcome-aligned AI workflows and verifiers, with reliable image output. | vendor's own |
| Hyreflow hyreflow.ai | MCP server | Recruitment automation: source, enrich, qualify and sequence candidates, push to your ATS. | vendor's own |
| Letmediff MCP letmediff.it | MCP server | The official Letmediff MCP server helping you review your code with an agent first workflow | vendor's own |
| Meertrack meertrack.com | MCP server | Competitive intelligence - track what competitors ship each week. 8 tools, 3 prompt workflows. | vendor's own |
| minitok minitok.dev | MCP server | Verified coding workflows with planning, verification, bounded retries, evidence, and evolution. | vendor's own, widely used |
| Outlit outlit.ai | MCP server | Outlit gives agents real-time understanding of customers to automate support and revenue workflows. | vendor's own |
| ProofSlip proofslip.ai | MCP server | Receipt-based verification for AI agent workflows — create, verify, and poll ephemeral proof objects | vendor's own |
| Roamer MCP mathismeadows.com | MCP server | Project registry, behavioral specs, and engineering threads for AI coding agent workflows. | vendor's own |
| Scope (Legal) scope.bid | MCP server | Dispatch litigation work to legal-services vendors from any MCP-compatible AI workflow. | vendor's own |
| ToolAPI toolapi.org | MCP server | Free public MCP for AI agents — 193 tools, 44 workflows. No API key. | vendor's own |
| Unity MCP shiranui-isuzu.dev | MCP server | Unity Editor automation for AI agents: scenes, prefabs, assets, shaders, Timeline, tests, builds. | vendor's own, widely used |
| VibeSEO vibeseo.dev | MCP server | SEO research, keyword discovery, site audits, Search Console, backlinks and content workflow. | vendor's own |
| YTDL RMCP dinglebear.ai | MCP server | yt-dlp search, download, metadata, delivery, and Plex workflows over MCP and CLI. | vendor's own |
How we test this category
One workflow across email, CRM and a database on every platform. We compare connection setup, authorisation, action coverage, retries, logs and the cost per completed run. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.