Join our Newsletter — 33% off our NHI Course
Home› Guides› MCP Client Support Tracker: Which Apps and IDEs…
Guide AI Platforms

MCP Client Support Tracker: Which Apps and IDEs Support Which MCP Features

PDF for newsletter subscribers · free to read online

← All guides
By NHI Mgmt Group, edited by Lalit Choda Updated 15 November 2026 14 min read
On this page

An MCP client is the part of an AI application (the host) that connects to Model Context Protocol servers, and no two clients implement the same slice of the protocol. A server that works in one coding assistant can fail, lose its prompts or skip its sign-in flow in another, because each client chooses which transports, primitives, authorisation flows and extensions it supports. This tracker records what eight widely used clients document today, and what the official MCP extension support matrix shows for a wider set. It is written for developers shipping MCP servers, platform teams standardising on a client, and security teams writing allowlists.

Last checked: 2026-11-15. Clients are listed alphabetically; order is never a ranking. Every cell comes from the client's own documentation or the MCP project's own pages, and where a client's documentation does not state a capability the cell says so.

This is an independent reference page from NHI Mgmt Group based on public provider documentation; it is not sponsored or endorsed by any provider.

Key takeaways

  • Tools are the common denominator. Every client tracked here documents MCP tools. Resources, prompts, elicitation and roots are documented by some clients and not mentioned by others, so a server that depends on them needs a fallback.
  • Streamable HTTP is the remote default, SSE is legacy. The HTTP+SSE transport is classed as Deprecated under the MCP feature lifecycle policy in the 2026-07-28 specification, yet several clients still accept SSE endpoints for compatibility.
  • OAuth support is now widespread but not identical. Clients differ on Client ID Metadata Documents, Dynamic Client Registration, pre-registered client IDs and RFC 9207 issuer validation, which the 2026-07-28 specification now requires clients to check when present.
  • Extensions are opt-in and unevenly adopted. The official extension matrix shows MCP Apps as the most widely ticked extension; OAuth Client Credentials, Enterprise-Managed Authorization and Skills are each listed for only a few clients, and the matrix has no Tasks column.
  • Admin controls decide what actually runs. Allowlists, managed configuration files, per-tool approval modes and trust flags are client-specific, so governance has to be configured once per client.

How to read this tracker

The MCP specification separates three roles: hosts (the LLM application), clients (connectors inside the host, one per server) and servers (which provide context and capabilities). Servers can offer three primitives, resources, prompts and tools, and clients can offer features back to servers such as elicitation. Optional features such as MCP Apps and Tasks sit outside the core protocol as official extensions that both sides must declare.

  • Documented: the client's own documentation describes the feature. It does not prove every edge case works.
  • Not stated by <provider>: the client's MCP documentation, as fetched on the check date, does not mention the feature. It may still exist, may be undocumented or may be planned.
  • Version sensitivity: clients release frequently. Where a document ties a feature to a release (for example a minimum CLI version), the tracker says so.

The MCP project used to publish a community feature support matrix for core primitives on its site. As of the check date the old clients address redirects to the getting started page, and the project's maintained matrix covers official extensions only (see the extension table below). For what MCP is and how the protocol works, see What Is MCP? The Model Context Protocol Explained; for spec revisions, see the MCP Specification Version Tracker.

Transports and authentication by client

As of 15 November 2026, from each client's MCP documentation.

Client (publisher)Local transportRemote transportRemote authentication documentedWhere servers are configured
ChatGPT (OpenAI)Not stated by OpenAIRemote server URL; the sample server uses SSE with a URL ending /sse/OAuth recommended; Client ID Metadata Documents where the authorisation server supports them, with public client (none) or private_key_jwt; Dynamic Client Registration when configuredChatGPT Plugins: "Add custom MCP server", then "Create as a plugin"
Claude Code (Anthropic)stdioHTTP (recommended; streamable-http accepted as an alias); SSE (deprecated); WebSocket via JSON configOAuth 2.0 via /mcp or claude mcp login; pre-configured client ID and secret; headersHelper for custom headersLocal and user scope in ~/.claude.json; project scope in .mcp.json
Codex CLI (OpenAI)STDIOStreamable HTTPOAuth is the default auth setting, with Client ID Metadata Documents and Dynamic Client Registration; codex mcp login; bearer_token_env_var; http_headers_helper~/.codex/config.toml, or .codex/config.toml in trusted projects, one [mcp_servers.<name>] table per server
Cursor (Cursor)stdioSSE and Streamable HTTPOAuth authorisation code flow with PKCE; registers as a public client under Dynamic Client Registration; static CLIENT_ID, optional CLIENT_SECRET and scopes for providers without itProject .cursor/mcp.json; global ~/.cursor/mcp.json; Extension API; Marketplace
Gemini CLI (Google)StdioSSE (url) and Streamable HTTP (httpUrl)OAuth 2.0 with automatic discovery on a 401 response; validates the iss parameter per RFC 9207; tokens stored in ~/.gemini/mcp-oauth-tokens.json; /mcp authmcpServers object in settings.json
goose (Agentic AI Foundation project, originated at Block)stdio extensionsStreamable HTTP extensions (streamable_http)OAuth for remote extensions, including a pre-registered client (client_id, secret key, scopes); callback on 127.0.0.1 with an ephemeral port, or GOOSE_OAUTH_CALLBACK_PORT~/.config/goose/config.yaml; CLI and desktop prompts; goose://extension deep links
Visual Studio Code with GitHub Copilot (Microsoft)Command (stdio)HTTP (HTTP or Server-Sent Events)Follow each publisher's authentication instructions; do not paste credentials into chat or shared configurationWorkspace .mcp.json and a personal Copilot Global configuration
Zed (Zed Industries)Local servers via commandRemote servers by urlStandard MCP OAuth flow when no Authorization header is configured; header-based tokens otherwisecontext_servers in Zed settings; Settings, AI, MCP Servers; Zed extensions

Transport choice has security consequences: a stdio server runs as a local process with the user's privileges, while a remote server's exposure depends on its authorisation. See Streamable HTTP vs stdio MCP Transport and, for servers still on SSE, MCP SSE to Streamable HTTP Migration.

Protocol features by client

As of 15 November 2026. "Documented" means the client's MCP page names the feature.

ClientToolsResourcesPromptsElicitationRootsOther features documented
ChatGPTDocumented; read-only search and fetch needed for deep research and company knowledgeNot stated by OpenAINot stated by OpenAINot stated by OpenAINot stated by OpenAIManual confirmation before any write action
Claude CodeDocumented; named mcp__<server>__<tool>Refreshed on list_changedRefreshed on list_changedDocumented (dialog; Elicitation hooks)Documented (roots/list)Tasks extension, public beta, v2.1.304 or later; channels
Codex CLIDocumented through enabled_tools and disabled_toolsNot stated by OpenAINot stated by OpenAINot stated by OpenAINot stated by OpenAIServer instructions returned at initialisation
CursorDocumentedDocumentedDocumentedDocumentedDocumentedMCP Apps
Gemini CLIDocumented; includeTools and excludeToolsDocumented; @server://resource/path references call resources/readDocumented as slash commandsNot stated by GoogleNot stated by Google/mcp status command
gooseDocumented (extensions supply tools; per-tool timeout)Not stated by the goose projectNot stated by the goose projectNot stated by the goose projectNot stated by the goose projectBuilt-in extensions; Code Mode for tool discovery
VS Code with GitHub CopilotDocumentedNot stated by MicrosoftNot stated by MicrosoftDocumented as server input requestsNot stated by MicrosoftMCP Apps (Experimental)
ZedDocumented; handles notifications/tools/list_changedNot stated by ZedDocumentedNot stated by ZedNot stated by ZedAgent profiles to scope which tools a model sees

The practical rule for server authors: put anything essential behind a tool. Resources and prompts improve the experience in clients that surface them, but a server whose core function depends on them will appear broken in a client that only lists tools. The distinctions between the three primitives are covered in MCP Tools vs Resources vs Prompts.

Official extension support matrix

The MCP project maintains a community-edited Extension Support Matrix. Extensions are always opt-in: a client only uses one if both client and server declare it in the extensions field of their capabilities. The table reproduces the matrix as of 15 November 2026, reordered alphabetically. "Listed" means the matrix ticks the client; "Partial" is the matrix's own label; "Not listed" means the matrix shows no entry, which can mean no support or no report.

ClientMCP AppsOAuth Client CredentialsEnterprise-Managed AuthorizationSkills over MCP
Archestra.AIListedNot listedListedNot listed
ChatGPTListedNot listedNot listedPartial
Claude (web)ListedNot listedNot listedNot listed
Claude DesktopListedNot listedNot listedNot listed
CursorListedNot listedNot listedNot listed
fast-agentNot listedNot listedNot listedPartial
GooseListedNot listedNot listedNot listed
MCP InspectorNot listedNot listedNot listedPartial
mcpc MCP CLINot listedListedListedListed
MCPJamListedNot listedNot listedNot listed
Microsoft 365 CopilotListedNot listedNot listedNot listed
PostHog CodeListedNot listedNot listedNot listed
PostmanListedNot listedNot listedNot listed
VS Code GitHub CopilotListedNot listedNot listedNot listed

Two cautions. First, the matrix does not cover every client or extension: Claude Code is not in it, though its documentation describes Tasks extension support as a public beta, so check both before relying on a feature. Second, the matrix notes that auth extension support is tracked separately from core MCP authorisation features such as Dynamic Client Registration and Client ID Metadata Documents. The security side of interactive UI extensions is covered in the MCP Apps Security Guide.

Admin and governance controls by client

As of 15 November 2026, from each client's MCP documentation. These are customer-side settings that decide which servers and tools can run.

ClientServer allow or deny controlsTool approval controls
ChatGPTAdding a custom server requires accepting a risk warning; workspace users go through an OAuth flow to the service. Workspace admin settings are not stated in OpenAI's MCP developer pageManual confirmation before any write action
Claude Codemanaged-mcp.json for exclusive control; managedMcpServers (v2.1.259 or later); enabledMcpjsonServers and disabledMcpjsonServers for project serversProject-scoped servers need approval in interactive sessions; claude mcp reset-project-choices
Codex CLIProject config loads only in trusted projects; required = true makes startup fail if a server is not readydefault_tools_approval_mode (auto, prompt, writes, approve); per-tool tools.<tool>.approval_mode
CursorEnterprise MCP Allowlist with command entries for stdio and URL entries for remote servers; team distribution under Dashboard, Plugins and MCPs; per-server network modesApproval before MCP tool use by default; Run Modes; optional per-server tool allowlists
Gemini CLImcp.allowed and mcp.excluded in settings.jsontrust: true bypasses confirmations for a server (default false in the documented example); includeTools and excludeTools
gooseExtensions enabled per configuration file or session (--with-builtin)goose operates autonomously by default; goose permission mode and tool permissions add approval
VS Code with GitHub CopilotMarketplace availability depends on organisation policy; trust requests to review before acceptingTool approval requests; review startup and sign-in requests
Zedenable_all_context_servers and per-profile context_serversTool permission confirm (default) or allow; per-tool rules keyed mcp:<server>:<tool_name>

Because each client has its own controls, an organisation that permits three clients has three allowlists to maintain. A gateway or registry can centralise this; see the MCP Gateway and MCP Server Governance Guide and MCP Gateway vs MCP Registry. Finding servers users have added themselves is covered in How to audit MCP servers on developer laptops.

What the 2026-07-28 specification changes for clients

The 2026-07-28 revision is the largest change to client behaviour since remote transports arrived. Clients built against 2025-11-25 keep working with older servers, but the following changes affect what a client must send and accept:

  1. Stateless protocol: the initialize handshake is removed; every request carries protocol version and client capabilities in _meta, and clients should identify themselves on each request.
  2. server/discover: servers must implement it; clients may call it first for version selection or as a compatibility probe on stdio.
  3. No protocol sessions: the Mcp-Session-Id header is removed from Streamable HTTP, and broken response streams are no longer resumable.
  4. Multi Round-Trip Requests: servers return an input_required result instead of sending server-initiated requests such as elicitation, so clients must retry the original request with the answers.
  5. Tasks moves to an extension: io.modelcontextprotocol/tasks replaces the experimental core tasks feature.
  6. Authorisation hardening: clients must validate a present iss against the recorded issuer (RFC 9207), specify application_type during Dynamic Client Registration, and key stored credentials by issuer.

The revision also deprecates Roots, Sampling and Logging (SEP-2577), reclassifies the HTTP+SSE transport as Deprecated, and deprecates Dynamic Client Registration in favour of Client ID Metadata Documents. Deprecated features remain functional for a minimum twelve-month window under the feature lifecycle policy. A client column that shows Roots or SSE today is therefore showing a feature on its way out. For the full authorisation model see the MCP Authorisation Specification Guide.

How to choose a client for MCP work

Factual criteria, not a ranking:

  • Primitive coverage: if your servers rely on resources or prompts, check the feature table; tools-only clients will hide them.
  • Remote authorisation: if your servers sit behind an enterprise identity provider, check whether the client supports Client ID Metadata Documents, pre-registered clients and issuer validation, and whether your authorisation server supports the same.
  • Central control: for regulated environments, prefer clients whose documentation describes a managed configuration or allowlist you can enforce, and confirm it applies to both stdio and remote servers.
  • Approval defaults: check whether tool calls need approval by default, and what setting removes it (trust, allow, auto modes). These settings are where most risky configurations start.
  • Small versus large organisations: a small team can manage per-user config files; a large organisation needs managed configuration, an inventory and a gateway, because per-client settings do not scale.

Where identity fits

Every remote MCP connection a client makes is a non-human access path: an OAuth token, an API key in an environment variable or a header produced by a helper script. Clients store these differently (Gemini CLI in a tokens file, others in config or the operating system), which matters for offboarding and incident response. Treat each client-to-server connection as a credential to inventory, scope and revoke. See API Keys vs OAuth for MCP Servers, the MCP Static Token Audit and How to give MCP servers and local agents secrets without plain-text config files.

Practitioner checklist

  • Record which MCP clients are approved in your organisation and the version of each, because feature support is release-dependent.
  • Test every server you publish in each approved client, and expose essential functions as tools rather than relying on resources or prompts.
  • Move remote servers from SSE to Streamable HTTP; the HTTP+SSE transport is Deprecated in the 2026-07-28 specification.
  • Configure the client's allowlist or managed configuration (for example mcp.allowed, the Cursor MCP Allowlist or managed-mcp.json) before rolling a client out widely.
  • Keep tool approval on for write actions; audit for trust: true, allow or auto-approval settings in shared and project config files.
  • Check that your authorisation server supports what each client uses: Client ID Metadata Documents, Dynamic Client Registration, PKCE and the RFC 9207 iss parameter.
  • Inventory the credentials each client holds for MCP servers and include them in offboarding and incident playbooks.
  • Re-check this matrix and each client's documentation before depending on an extension such as MCP Apps or Tasks.

Standards and references

Related NHI Mgmt Group resources: MCP Security Guide, MCP Servers Hub, Local MCP Server Security Guide, MCP vs A2A, AI Agent Platforms Compared.

PDF for subscribers

Take this guide with you

Every section, table and checklist in one PDF, with links to the sources and related guides. Subscribe to our weekly NHI & AI Identity Journal and we’ll email you a download link.

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.

NHIMG Editorial Note
Researched and written by the NHI Mgmt Group editorial team using AI tools, under the editorial direction of Lalit Choda. Facts are drawn from the sources listed on this page and checked by our automated quality process. Last updated 15 November 2026. Spotted an error? Use our contact page.
NHI Mgmt Group, the independent authority on Non-Human Identity, IAM and Agentic AI security. nhimg.org

PDF Downloads for Newsletter Subscribers

Get the guide

Enter your details and we’ll email you a download link.

The full guide is free to read online. The PDF is a thank you for subscribing.

Fill in all fields marked * and tick the PDF box to continue.