Skip to content

MCP Infrastructure & Registries Arena

MCP Infrastructure & Registries arenaBuyer checklist

Every requirement we judge mcp infrastructure & registries products against, as a ready-to-send RFP checklist — with each item's priority, why it matters, and how the top-ranked products score on it today.

52 requirements · 13 themes · verdicts for 6 products · updated 2026-09-10 · priorities mirror the story weights our scoring uses (methodology)

Procurement report →
Show the markdown export
# MCP Infrastructure & Registries — buyer checklist (RFP)

Derived from ProductArena's evidence-graded user-story taxonomy for MCP Infrastructure & Registries: 52 judged requirements. Priorities mirror story weights (3 = must-have, 2 = should-have, 1 = nice-to-have).

## Agenticness

- [ ] **[must-have]** Plug MCP servers into this product so it can use their tools
- [ ] **[must-have]** Connect an agent via an official MCP server
- [ ] **[must-have]** Drive the product through a documented public API
- [ ] **[must-have]** Delegate tasks to a built-in AI assistant inside the product
- [ ] **[should-have]** Point an agent at llms.txt or agent-oriented docs
- [ ] **[should-have]** Run the product headlessly / in CI for automation
- [ ] **[should-have]** Use an official CLI
- [ ] **[should-have]** Issue scoped/least-privilege API credentials for an agent
- [ ] **[should-have]** Build against official SDKs
- [ ] **[should-have]** Subscribe to events via webhooks
- [ ] **[should-have]** Get AI-generated insights and suggestions from my data inside the product
- [ ] **[should-have]** Set up automations that run autonomously in the background
- [ ] **[should-have]** Operate the product with natural-language commands
- [ ] **[should-have]** Explore an interactive API reference with runnable examples
- [ ] **[should-have]** Download a machine-readable API spec (OpenAPI or equivalent)
- [ ] **[should-have]** Rely on versioned APIs with a documented deprecation policy
- [ ] **[nice-to-have]** Test against a sandbox environment without touching production data

## Auth credentials

- [ ] **[must-have]** Maintain separate connected accounts and scoped tokens per end user of my product, so each user's agent acts only on that user's credentials
- [ ] **[must-have]** Let the platform run OAuth flows for downstream tools and vault the resulting credentials encrypted, with automatic token refresh
- [ ] **[nice-to-have]** White-label the authorization flow with my own branding and my own OAuth app credentials

## Automation depth

- [ ] **[must-have]** Define rules that trigger actions automatically on events
- [ ] **[should-have]** Perform bulk operations across many items at once
- [ ] **[should-have]** Schedule recurring jobs or workflows
- [ ] **[nice-to-have]** Version, review, and roll back my automations

## Deployment self host

- [ ] **[nice-to-have]** Bridge a locally running MCP server into the platform as a managed remote connection without deploying it

## Gateway controls

- [ ] **[should-have]** Restrict which servers and individual tools an agent may call through allowlists or per-tool access control
- [ ] **[should-have]** See a log of every tool call that passed through the platform, with enough detail to audit or replay what an agent did

## Hosted servers

- [ ] **[must-have]** Reach a deep catalog of third-party apps and APIs (hundreds to thousands of integrations) through the platform
- [ ] **[must-have]** Point my MCP-compatible client at a hosted remote server URL and reach downstream tools without deploying any infrastructure
- [ ] **[should-have]** Turn an existing API definition (OpenAPI) or custom code into a hosted MCP server without writing protocol plumbing
- [ ] **[should-have]** Publish my own MCP server on the platform for distribution, discovery, and installation by others
- [ ] **[should-have]** Subscribe my agent to events from connected downstream apps (triggers/webhooks) instead of polling them

## Observability analytics

- [ ] **[should-have]** See usage analytics for the servers and tools my org consumes or publishes — call volumes, users, errors, and cost

## Openness

- [ ] **[must-have]** Export all of my data in open formats and leave
- [ ] **[must-have]** Self-host the core product
- [ ] **[should-have]** Do everything through the API that I can do in the UI
- [ ] **[should-have]** Read the product's source under an open license

## Pricing plans

- [ ] **[should-have]** See transparent pricing per tool call or connection plus documented rate limits before committing to the platform
- [ ] **[nice-to-have]** Prototype my agent's tool connections on a meaningful free tier before paying anything

## Privacy posture

- [ ] **[must-have]** Prevent my data from being used to train AI models
- [ ] **[should-have]** Choose where my data is stored (region/residency)
- [ ] **[should-have]** Control data retention and deletion
- [ ] **[should-have]** Opt out of telemetry and usage tracking

## Registry discovery

- [ ] **[must-have]** Query the platform's registry or catalog through a documented API to discover servers and tools programmatically
- [ ] **[must-have]** Search and browse a large catalog of MCP servers and tools by capability before wiring anything into my agent
- [ ] **[should-have]** Inspect a listed server's tools, input schemas, transport, and hosting attributes before connecting to it
- [ ] **[should-have]** Exercise an MCP server's tools from a browser-based inspector or playground before integrating it

## Sdk clients

- [ ] **[should-have]** Drive the publish-and-deploy workflow from an official CLI — authenticate, stage or build a server, push it, and install it into agents
- [ ] **[should-have]** Plug the platform's tools into major agent frameworks and SDKs (Vercel AI SDK, LangChain, CrewAI, OpenAI or Anthropic SDKs) with documented adapters

## Tool curation quality

- [ ] **[should-have]** Rely on the platform scanning or inspecting listed servers for malicious or vulnerable behavior before my agents use them
- [ ] **[should-have]** Compare servers using published quality signals — usage counts, health or liveness checks, scores, or verification badges
- [ ] **[should-have]** Search and load tools at runtime through meta-tools instead of having thousands of tool definitions stuffed into my context

---

Source: https://ultrametric.ai/productarena/arena/mcp-infrastructure (evidence-graded verdicts for 6 products) · methodology: https://ultrametric.ai/productarena/methodology

Chips show the top 5 ranked products' current verdict on each requirement — ✓ full · ~ partial · ! disputed · — none · n/a not applicable.

Agenticness — how well agents can access and operate the productAgenticness· 17 items

How well agents can access and operate the product

Auth credentials — stories about auth credentials in this arenaAuth credentials· 3 items

Stories about auth credentials in this arena

  • platform-engineerMaintain separate connected accounts and scoped tokens per end user of my product, so each user's agent acts only on that user's credentials

    Core requirement — weighs 3× in arena scoring · 2 of 6 products fully deliver this today

    must-have
  • developerLet the platform run OAuth flows for downstream tools and vault the resulting credentials encrypted, with automatic token refresh

    Core requirement — weighs 3× in arena scoring · 2 of 6 products fully deliver this today

    must-have
  • platform-engineerWhite-label the authorization flow with my own branding and my own OAuth app credentials

    Differentiator, not a dealbreaker — weighs 1× in arena scoring · no product fully delivers this yet

    nice-to-have

Automation depth — how much of the product can run unattendedAutomation depth· 4 items

How much of the product can run unattended

Deployment self host — stories about deployment self host in this arenaDeployment self host· 1 item

Stories about deployment self host in this arena

  • developerBridge a locally running MCP server into the platform as a managed remote connection without deploying it

    Differentiator, not a dealbreaker — weighs 1× in arena scoring · 2 of 6 products fully deliver this today

    nice-to-have

Gateway controls — stories about gateway controls in this arenaGateway controls· 2 items

Stories about gateway controls in this arena

  • platform-engineerRestrict which servers and individual tools an agent may call through allowlists or per-tool access control

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 6 products fully deliver this today

    should-have
  • platform-engineerSee a log of every tool call that passed through the platform, with enough detail to audit or replay what an agent did

    Important, not disqualifying — weighs 2× in arena scoring · 1 of 6 products fully deliver this today

    should-have

Hosted servers — stories about hosted servers in this arenaHosted servers· 5 items

Stories about hosted servers in this arena

Observability analytics — stories about observability analytics in this arenaObservability analytics· 1 item

Stories about observability analytics in this arena

  • platform-engineerSee usage analytics for the servers and tools my org consumes or publishes — call volumes, users, errors, and cost

    Important, not disqualifying — weighs 2× in arena scoring · 1 of 6 products fully deliver this today

    should-have

Openness — open source, data portability, and self-hosting storiesOpenness· 4 items

Open source, data portability, and self-hosting stories

Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans· 2 items

Plan structure and value — what each tier costs and what it unlocks

Privacy posture — data-handling and privacy storiesPrivacy posture· 4 items

Data-handling and privacy stories

Registry discovery — stories about registry discovery in this arenaRegistry discovery· 4 items

Stories about registry discovery in this arena

  • ai agentQuery the platform's registry or catalog through a documented API to discover servers and tools programmatically

    Core requirement — weighs 3× in arena scoring · 3 of 6 products fully deliver this today

    must-have
  • developerSearch and browse a large catalog of MCP servers and tools by capability before wiring anything into my agent

    Core requirement — weighs 3× in arena scoring · 2 of 6 products fully deliver this today

    must-have
  • developerInspect a listed server's tools, input schemas, transport, and hosting attributes before connecting to it

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • developerExercise an MCP server's tools from a browser-based inspector or playground before integrating it

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 6 products fully deliver this today

    should-have

Sdk clients — stories about sdk clients in this arenaSdk clients· 2 items

Stories about sdk clients in this arena

  • developerDrive the publish-and-deploy workflow from an official CLI — authenticate, stage or build a server, push it, and install it into agents

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • developerPlug the platform's tools into major agent frameworks and SDKs (Vercel AI SDK, LangChain, CrewAI, OpenAI or Anthropic SDKs) with documented adapters

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have

Tool curation quality — stories about tool curation quality in this arenaTool curation quality· 3 items

Stories about tool curation quality in this arena

  • platform-engineerRely on the platform scanning or inspecting listed servers for malicious or vulnerable behavior before my agents use them

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • developerCompare servers using published quality signals — usage counts, health or liveness checks, scores, or verification badges

    Important, not disqualifying — weighs 2× in arena scoring · no product fully delivers this yet

    should-have
  • ai agentSearch and load tools at runtime through meta-tools instead of having thousands of tool definitions stuffed into my context

    Important, not disqualifying — weighs 2× in arena scoring · 2 of 6 products fully deliver this today

    should-have

Full evidence behind every verdict lives on the arena page and each product page — chips above deep-link straight to the judged story.