Metorial vs Claude Team / Enterprise

Claude Team / Enterprise (connectors, skills, admin controls) governs AI inside its own products. Metorial delivers the same approved tools and skills into every AI client your company uses.

Where Claude Team / Enterprise wins: Bundled with the Claude seat: connectors, org-wide skills and SSO come in the $20/seat Team plan with no extra gateway to buy or run.

Metorial is the stronger fit if you want delivery into the AI clients people already use, self-hosting and Git-synced skills.

Every Claude Team / Enterprise fact below links to Claude Team / Enterprise's own page. Anything they don't publish is marked "Not published", not "No".

Where Claude Team / Enterprise wins

  • Bundled with the Claude seat: connectors, org-wide skills and SSO come in the $20/seat Team plan with no extra gateway to buy or run.source
  • Enterprise RBAC sets each connector to Always allow, Needs approval, Blocked or Custom per group, down to individual tools, natively inside the client.source
  • Large first-party directory (829 connectors, many 'Anthropic verified') plus Okta-based Enterprise-managed connector auth (GA Aug 2026).source

Key differences

Each cell links to the page it comes from.

FeatureMetorialClaude Team / Enterprise
Source licenseFSL-1.1-ALv2 engine (Apache 2.0 after two years); Apache-2.0 integration catalogsourceThe engine (metorial-platform) is source-available under FSL and converts to Apache 2.0 two years after each release. The integration catalog (metorial/metorial) is Apache-2.0.Not publishedClosed SaaS.
Self-hostYessourceNot published
Integration catalog1,000+source829 connectors in Anthropic directorysourceCount shown on directory page on 2026-10-17.
One URL for all toolsYessourceNot publishedEach connector is added separately; no single aggregated endpoint described.
Per-user OAuthYessourceYessource
SSO (SAML or OIDC)YessourceYessourceTeam and Enterprise.
SCIM provisioningYessourcePartialsourceEnterprise only.
Role or group-based tool accessYessourcePartialsourceEnterprise only. Cowork admin guide notes Cowork has no per-group connector control.
Audit log per personYessourcePartialsourceLogged events cover sign-in, membership, projects, files, conversations; connector/tool calls not listed. Audit logs do not cover Cowork yet.
Create and edit skillsYessourceYessourceAnnounced Dec 18, 2025.
Git sync for skillsYessourcePartialsourceRepo-based skills apply to Claude Code; no Git sync for org skills in claude.ai described.
Own chat app requiredNosourceYessourceUsers must work in Claude apps (or Claude Code).
Prompt-injection detectionYessourceNot published
EU data regionYessourcePartialsourcePage covers Claude via AWS Bedrock / GCP Vertex / Microsoft Foundry, not claude.ai Enterprise.
SOC 2 Type IIYessourceYessource
LLM gateway or model routingNoNot publishedClaude models only; not a multi-model gateway.
Starting price$0 (Dev); Scale from $250/monthsource$20/seat/month (Team Standard, annual); Enterprise $20/seat/month + API-rate usagesource

Which AI clients each works in

FeatureMetorialClaude Team / Enterprise
Claude (web and desktop)YessourceYessource
Claude CodeYessourceYessourceClaude Code has its own managed-mcp.json / allowlist controls.
ChatGPTYessourceNosourceStructural: connectors and admin controls only apply to Claude surfaces.
CursorYessourceNosourceStructural: governs Claude surfaces only.
CodexYessourceNosourceStructural: governs Claude surfaces only.
GitHub CopilotYessourceNosourceStructural: governs Claude surfaces only.
Custom agents (SDK or API)YessourceNot published

Full checklist

Every row we track, with what it means. "Not published" means the vendor's own pages don't say.

Connect

FeatureMetorialClaude Team / Enterprise
Integration catalogHow many ready-made integrations or MCP servers the vendor publishes.1,000+source829 connectors in Anthropic directorysourceCount shown on directory page on 2026-10-17.
Verified or official serversThe catalog includes servers the vendor tests or maintains, not only community listings.YessourceYessourceLabel on many listings; verification process not described on the page. Claude Code docs say Anthropic reviews against listing criteria but 'doesn't security-audit or manage any MCP server'.
Bring your own MCP serverYou can add an MCP server you built or host yourself.YessourceYessourceCustom connectors; on Team only Owners/Primary Owners can add them.
Remote (HTTP) MCP serversConnects to MCP servers hosted elsewhere over HTTP.YessourceYessourceCustom connectors are remote MCP servers.
Local, stdio or Docker serversRuns MCP servers that ship as local processes or containers.YessourcePartialsourceLocal servers work via Claude Desktop config and Claude Code (stdio), not in claude.ai or Cowork.
One URL for all toolsA user adds one endpoint to their AI client and reaches every approved tool through it.YessourceNot publishedEach connector is added separately; no single aggregated endpoint described.
Version pinningYou can lock an integration to a known version.YessourceNot published
Schema change monitoringChanges to tool definitions are detected and flagged.YessourceNot published

AI clients

FeatureMetorialClaude Team / Enterprise
Claude (web and desktop)Documented to work in the Claude apps.YessourceYessource
Claude CodeDocumented to work in Claude Code.YessourceYessourceClaude Code has its own managed-mcp.json / allowlist controls.
ChatGPTDocumented to work in ChatGPT.YessourceNosourceStructural: connectors and admin controls only apply to Claude surfaces.
CursorDocumented to work in Cursor.YessourceNosourceStructural: governs Claude surfaces only.
CodexDocumented to work in Codex.YessourceNosourceStructural: governs Claude surfaces only.
GitHub CopilotDocumented to work in GitHub Copilot.YessourceNosourceStructural: governs Claude surfaces only.
Custom agents (SDK or API)Your own agents can use the tools through an SDK or API.YessourceNot published
Own chat app requiredYes means people must work inside the vendor’s own app rather than the AI client they already use.NosourceYessourceUsers must work in Claude apps (or Claude Code).

Identity and access

FeatureMetorialClaude Team / Enterprise
Per-user OAuthTool calls run with each person’s own account, not a shared key.YessourceYessource
Managed OAuth appsThe vendor provides OAuth apps so you don’t register your own.YessourceNot publishedEnterprise-managed auth (Okta, Aug 2026) provisions connector access through the IdP for a listed set of connectors; not the same as vendor-managed OAuth apps.
Bring your own OAuth appYou can use OAuth apps registered under your own company.YessourceYessource
SSO (SAML or OIDC)People sign in through your identity provider.YessourceYessourceTeam and Enterprise.
SCIM provisioningUsers and groups sync automatically from your identity provider.YessourcePartialsourceEnterprise only.
Role or group-based tool accessAccess to tools follows roles or groups.YessourcePartialsourceEnterprise only. Cowork admin guide notes Cowork has no per-group connector control.
Tool-level allow and denyIndividual tools can be allowed or blocked, not only whole servers.YessourcePartialsourceEnterprise RBAC only; users can also disable tools per conversation.
Read-only modesAn integration can be limited to read-only tools.YessourceNot published

Visibility and security

FeatureMetorialClaude Team / Enterprise
Audit log per personEvery call is recorded and tied to the person or agent who made it.YessourcePartialsourceLogged events cover sign-in, membership, projects, files, conversations; connector/tool calls not listed. Audit logs do not cover Cowork yet.
Call tracingTool arguments and results are recorded for debugging and review.YessourcePartialsourceVia OpenTelemetry export in Claude Code (and Cowork OTEL); not documented for claude.ai chat.
Log export or SIEMLogs can be exported or streamed to your security tools.YessourcePartialsourceEnterprise Compliance API provides chats, files and audit events; OTEL for Cowork/Claude Code.
Data redaction or DLPSensitive data in tool traffic can be detected, masked or blocked.YessourceNot publishedCompliance API is used by third-party security platforms; no native DLP described.
Prompt-injection detectionTool traffic is inspected for prompt-injection attacks.YessourceNot published
Tool-poisoning protectionMalicious or changed tool descriptions are detected.YesThrough Protoguard.Not published

Skills

FeatureMetorialClaude Team / Enterprise
Create and edit skillsTeams can write and edit shared skills in the product.YessourceYessourceAnnounced Dec 18, 2025.
Git sync for skillsSkills sync to or from a Git repository.YessourcePartialsourceRepo-based skills apply to Claude Code; no Git sync for org skills in claude.ai described.
Skills delivered by roleSkills reach people based on their role or group.YessourceNot publishedOrg skills are on by default for everyone; plugin marketplace supports group-level overrides per admin guide, skills targeting by group not stated.
Skills over MCPSkills are served to AI clients through MCP.Not publishedNot published

Deployment

FeatureMetorialClaude Team / Enterprise
Source licenseThe license the product’s code is published under, if any.FSL-1.1-ALv2 engine (Apache 2.0 after two years); Apache-2.0 integration catalogsourceThe engine (metorial-platform) is source-available under FSL and converts to Apache 2.0 two years after each release. The integration catalog (metorial/metorial) is Apache-2.0.Not publishedClosed SaaS.
Self-hostYou can run it on your own infrastructure.YessourceNot published
VPC or on-premCan be deployed in your own cloud account or data center.YessourceNot published
Air-gappedCan run with no internet connection.YesNot published
EU data regionData can be hosted in the EU.YessourcePartialsourcePage covers Claude via AWS Bedrock / GCP Vertex / Microsoft Foundry, not claude.ai Enterprise.

Compliance

FeatureMetorialClaude Team / Enterprise
SOC 2 Type IIHolds a SOC 2 Type II report.YessourceYessource
ISO 27001Holds ISO/IEC 27001 certification.Not publishedYessourceAlso ISO/IEC 42001:2023.
HIPAASupports HIPAA workloads, usually with a BAA.YesSigns BAAs.PartialsourceEnterprise only; BAA available per certifications article.
GDPR and DPAStates GDPR compliance and offers a data processing agreement.YessourceA data processing agreement is published at /legal/data-processing-agreement.Yessource

Pricing

FeatureMetorialClaude Team / Enterprise
Public pricingPrices are published on the vendor’s site.YessourceYessource
Free tierA free plan or free edition exists.YessourcePartialsourceIndividual Free plan only; Team and Enterprise are paid.
Starting priceThe lowest published paid price, as listed.$0 (Dev); Scale from $250/monthsource$20/seat/month (Team Standard, annual); Enterprise $20/seat/month + API-rate usagesource
Pricing modelHow the vendor charges: per seat, usage, platform fee, or a mix.Flat monthly plans with paid add-ons (extra seats, tool calls)sourcePer seat (Team); per seat plus metered usage at API rates (Enterprise)source

Model layer

FeatureMetorialClaude Team / Enterprise
LLM gateway or model routingRoutes model traffic, not only tool traffic.NoNot publishedClaude models only; not a multi-model gateway.
Cost tracking per personShows AI spend per person or team.NoPartialsourceEnterprise with usage credits on; covers Claude spend only.

Which should you pick?

SituationPickWhy
Rolling AI out to every employee in the clients they already useMetorialClaude Team / Enterprise has people work in its own app; Metorial delivers tools into Claude, ChatGPT, Cursor and others.
You must self-hostMetorialMetorial documents self-hosting; Claude Team / Enterprise's own pages don't state a self-hosted option.
You need an LLM gateway or model routing todayA dedicated model routerMetorial doesn't ship an LLM gateway, and Claude Team / Enterprise's pages don't state one.
Teams should share skills, not only toolsEitherBoth document shared skills; compare the Skills rows below.
You are building integrations into your own productMetorialOnly one side documents an SDK or API for your own agents.

Pricing

Published prices only. Nothing is estimated.

Metorial

  • Metorial Dev: $0 monthsource
  • Metorial Scale: $250 monthsource
  • Metorial for Enterprise: Contact salessource

Claude Team / Enterprise

  • Free: $0 per user/monthsource
  • Team – Standard seat: $20 annual / $25 monthly per seat/month, 2–150 seatssource
  • Team – Premium seat: $100 annual / $125 monthly per seat/monthsource
  • Enterprise: US$20 + usage billed at API rates per seat/month, billed annually, 20-seat minimumsource
  • Enterprise usage billed at standard API rates on top of the seat fee
  • Per-member spend limits via Spend Limits API (Enterprise, usage credits on)

What each Metorial plan includes

From the Metorial pricing page.

IncludedMetorial DevMetorial ScaleMetorial for Enterprise
Tool calls per month500,0002,500,000Custom
Callbacks10,000100,000Custom
Workforce seats220Custom
Provider integrations10UnlimitedUnlimited
Log retention30 days90 daysCustom
Production accessNot includedIncludedIncluded

On every plan

  • Slack and email support
  • Auth Connections: Unlimited
  • Sessions: Unlimited
  • Concurrent Connections: Unlimited
  • Developer API Access
  • Custom Integrations
  • Remote MCP Servers
  • Managed MCP Servers

Claude Team / Enterprise limits

As published by the vendor.

  • Team seats: 2 to 150 seatssource
  • Enterprise minimum: 20 seats, billed annuallysource
  • Custom connectors on Free: 1source
  • Audit log export window: Past 180 days per export; download link valid 24 hourssource
  • Enterprise-managed connector auth IdP: Okta only at launchsource

Moving from Claude Team / Enterprise to Metorial

  • Remote MCP servers you use through Claude Team / Enterprise can be added to Metorial as they are.
  • OAuth apps registered under your company can be reused, so people sign in the way they do today.
  • Sign-in moves to your identity provider through SAML; groups decide who gets which tools.
  • Skills, policies and audit history in Claude Team / Enterprise don't transfer automatically. Talk to us about moving them.

Book a demo to plan the move with us.

Frequently asked questions

Common questions about Metorial and Claude Team / Enterprise.

  1. Is Claude Team / Enterprise open source?
    Claude Team / Enterprise's own pages don't state a source license.
  2. Claude Team / Enterprise's own pages don't say whether it can be self-hosted.
  3. Claude Team / Enterprise's own pages say ChatGPT is not supported.
  4. Metorial's Dev plan is free and Scale starts at $250 a month. Claude Team / Enterprise publishes Free at $0 per user/month and Team – Standard seat at $20 annual / $25 monthly per seat/month, 2–150 seats. The right answer depends on team size; see the pricing section.
  5. Yes. Metorial is SOC 2 Type 2 and GDPR compliant, with EU and US regions.
  6. Metorial's engine is published under FSL-1.1-ALv2 engine (Apache 2.0 after two years); Apache-2.0 integration catalog. You can self-host it or use the hosted platform.

Checked October 17, 2026. 33 Claude Team / Enterprise facts are sourced, each linked in its row. Spotted something wrong? Tell us and we will fix it. All product names are trademarks of their owners.

Try Metorial next to Claude Team / Enterprise

Start free, self-host from GitHub, or talk to us about your rollout.