Does Relevance AI support MCP?

Yes, bidirectionally — it can consume external MCP servers and expose its own tools to MCP clients like Claude Desktop, Cursor, and VS Code.

Is there a free tier?

Yes — a one-time 1,000 Vendor Credits plus 200 Actions per month, with paid top-ups beyond that.

ManagedNot yet hands-on tested

Relevance AI

The enterprise platform for agents you can trust at scale.

What it is

Relevance AI is a low/no-code cloud platform for building, deploying, and managing autonomous AI agents and multi-agent "workforces" that run business playbooks across GTM, sales, marketing, support, research, and ops. Agents are created via natural language, drag-and-drop, or programmatically.

At a glance

7/7 facts sourced

Pricing: Usage-based on two units — an "Action" (a tool run) and "Vendor Credits" (model cost). Free sign-up includes a one-time 1,000 Vendor Credits plus 200 Actions/month; top-ups are $80 per 1,000 Actions and $20 per 10,000 Vendor Credits; Enterprise is contact-sales.source ↗
Hosting model: Fully-managed cloud SaaS; no self-host option is documented.source ↗
Memory & state: A "Knowledge" RAG feature — upload files or sync Google Drive, SharePoint, Notion, and websites to ground agents.source ↗
MCP support: Nativesource ↗
Integrations: The homepage cites 1,000+ apps (HubSpot, Salesforce, Slack, Gmail, LinkedIn, Apollo, Notion), with Enterprise referencing 2,000+.source ↗
Model providers: Multi-provider routing across Claude (Anthropic), Gemini (Google), and GPT (OpenAI).source ↗
Open source: Nosource ↗

4.0of 5

Editorial scorecard

Overall 4.0 / 5

Our opinion — the same 0–5 rubric is applied to every platform, including Alfe. See the rubric.

Developer experience4/5

Pricing transparency & value3/5

Scalability4/5

Memory & state3/5

Integrations5/5

MCP nativeness5/5

Strengths

Native bidirectional MCP — consume external servers and expose Relevance tools to MCP clients.
Multi-provider model routing across Claude, Gemini, and GPT.
Broad integrations plus built-in "Knowledge" RAG grounding.

Trade-offs

No documented self-host option.
Full-featured/enterprise use is gated behind contact-sales.
Two-axis billing (Actions plus Vendor Credits) makes cost estimation harder.

Our take

Editorial opinion — not a hands-on test result

In our opinion, Relevance AI is a strong candidate for teams that want to stand up business-function "agent workforces" quickly with low code, broad connectors, and native MCP. The main things to weigh are the two-axis usage billing and the enterprise-sales gate for the fuller feature set. Its multi-provider routing and RAG grounding are genuine strengths.

FAQ

Does Relevance AI support MCP?: Yes, bidirectionally — it can consume external MCP servers and expose its own tools to MCP clients like Claude Desktop, Cursor, and VS Code.
Is there a free tier?: Yes — a one-time 1,000 Vendor Credits plus 200 Actions per month, with paid top-ups beyond that.

Compare Relevance AI

Sources

Relevance AI homepage · accessed 2026-07-01
Relevance AI plans & credits docs · accessed 2026-07-01
Relevance AI MCP docs · accessed 2026-07-01
Relevance AI pricing · accessed 2026-07-01

The Agent Examiner editorial · last updated 2026-07-01. Facts are drawn from each vendor’s own public materials; scores are our editorial opinion (methodology).

Product and company names are trademarks of their respective owners and are used here only to identify the products under discussion.