Skip to content
Weavz
Menu

Weavz MCP App

Connect Weavz directly from Claude, ChatGPT, Codex, Cursor, and other remote MCP clients.

Choose For your AI in the dashboard to connect apps and find client-specific installation instructions under Home or AI clients. You can use For your product when building for your own customers. Both experiences use the same authorized MCP Workspace and accounts.

The Weavz MCP App is the fastest way to use a Weavz workspace inside AI clients that support remote MCP connectors. Add the Weavz connector URL, sign in, choose the workspace the agent should use, and let Weavz expose the workspace's configured integrations through Code Mode.

Use this guide for Claude, ChatGPT, Codex, Cursor, Claude Code, and other MCP-compatible agents when the user experience should stay inside the AI client as much as possible.

Remote MCP connector
Try Weavz inside the agent you already use.
Add one hosted connector URL, sign in, and choose a workspace if asked. Available MCP features depend on your plan and client.
Connector name
Weavz MCP Workspace
Connector URL
https://platform.weavz.io/mcp/weavz
ChatGPT description
Connect to governed Weavz workspace tools through MCP.
Try in Claude
Give Claude access to the apps in your MCP Workspace.
Open Claude setup
1Select Add to Claude and review the Weavz name and URL.
2Sign in to Weavz and approve the requested access.
3Enable Weavz in a Claude chat, then ask it to list your apps.
Try in ChatGPT
Use your connected apps in a ChatGPT conversation.
Open ChatGPT connectors
1Open ChatGPT Plugins, then use the + menu and choose Add custom MCP server.
2Enter the Weavz connector name and HTTPS endpoint.
3Choose OAuth, acknowledge the tool risks, and select Create as a plugin. Complete Weavz sign-in and choose a workspace if asked.
4Review the discovered tools and install the resulting plugin. In a new chat, type @ and select Weavz.
5If your workspace uses the legacy Settings → Apps → Create flow, use Scan Tools, complete OAuth, then select Create.
Coding agents
See setup
Claude Code
claude mcp add --transport http weavz 'https://platform.weavz.io/mcp/weavz' claude mcp login weavz claude mcp list
Codex CLI
codex mcp add weavz --url 'https://platform.weavz.io/mcp/weavz' codex mcp login weavz
Cursor
{ "mcpServers": { "weavz": { "type": "http", "url": "https://platform.weavz.io/mcp/weavz" } } }
OpenCode
{ "$schema": "https://opencode.ai/config.json", "mcp": { "weavz": { "type": "remote", "url": "https://platform.weavz.io/mcp/weavz", "enabled": true } } }
Generic remote MCP URL
https://platform.weavz.io/mcp/weavz
Client surface preview
Weavz MCP App
W
Weavz Agent Workspace
Connected to this chat
Live
Agent Browser
Deterministic browser control
Ready
Filesystem
End-user scoped files
Ready
State KV
Durable agent memory
Ready
GitHub
Connect this user's account
Connect
MCP tools
3
Approvals
0
Add integrationHuman Gates
The connector UI gives users a visible control surface for integration status, connect links, approvals, and dashboard handoff while the agent gets the same workspace through MCP tools.

Connector URL

Use your Weavz platform URL plus /mcp/weavz.

text
https://platform.weavz.io/mcp/weavz

For self-hosted or private deployments, replace the host with your public Weavz API host:

text
https://your-weavz-domain.example.com/mcp/weavz

The endpoint must be reachable by the MCP client over HTTPS. A connector URL that only works from your laptop, VPN, or private office network will not work for hosted clients unless you provide a public tunnel or allow that traffic.

Fast Client Setup

Use the setup panel above when you are adding Weavz to a hosted AI client or a coding agent. For Claude, open the connector setup and approve Weavz sign-in. For ChatGPT, create a custom MCP app from connector settings, paste the Weavz connector URL, and let Weavz handle sign-in, workspace selection, and token scoping.

Use each client's current connector flow during rollout. Weavz keeps the product contract stable: one HTTPS connector URL, OAuth sign-in, one selected workspace, and user-owned connected accounts behind that workspace.

What Users See

  1. The user adds the Weavz connector in the MCP client.
  2. The client opens Weavz sign-in.
  3. If the user belongs to more than one workspace, Weavz asks which workspace this connector should use.
  4. Weavz shows the connector authorization screen.
  5. The client receives an MCP token scoped to that one workspace.
  6. In clients that support MCP app UI, the user can open the Weavz MCP App inside the client to add integrations, connect or reconnect user-owned credentials, refresh status, view pending approvals, and open the dashboard for advanced settings. Plain remote MCP clients still receive the same tools, but users manage integrations from the dashboard or connector authorization flow.

If a signed-in user has exactly one workspace, Weavz uses that workspace without showing an extra chooser. If a new user has no workspace yet, Weavz creates a starter workspace named Weavz Agent Workspace with Code Mode, Agent Browser, Agent Browser AI, Filesystem, State KV, memory, scratchpad, web reading, HTTP, and common SaaS integrations.

The workspace is selected during sign-in so the connector token stays scoped. To use a different workspace, disconnect or reauthorize the Weavz connector and choose the other workspace during the sign-in flow.

Choose The Right Setup

ScenarioRecommended path
A user wants Weavz inside Claude, ChatGPT, Codex, or another remote MCP clientUse the Weavz MCP App at /mcp/weavz
Your team wants to publish one general Weavz connector for broad useUse the Weavz MCP App and submit the same remote MCP endpoint where the platform supports app review
Your product needs one workspace-specific server with a curated URLUse the MCP Workspace’s included endpoint; optionally configure Code Mode or Tool Mode
Your backend provisions MCP clients for known end usersCreate an MCP Workspace and issue private workspace access tokens

The Weavz MCP App uses Code Mode by default. Agents get weavz_search, weavz_read_api, and weavz_execute for compact, dynamic use of the selected workspace. Use weavz_open_app to open the visual app-management surface in a compatible client. Focused app tools list and search apps, add or remove a configured alias, and create a user-scoped connection link. Older clients can still call the compatible weavz_app tool. UI support and availability depend on the client; a setup guide is not a claim of directory acceptance.

The starter workspace exposes browser tools as weavz.browser. It also exposes Agent Browser AI as weavz.browser_ai; those natural-language browser actions require the user to connect a model provider before they can run.

Common starter aliases:

AliasWhat agents use it for
weavz.browserDeterministic browser control with screenshots and human handoff
weavz.browser_aiNatural-language browser actions using a connected model provider
weavz.filesFilesystem artifacts and generated files
weavz.stateSmall durable key-value state
weavz.memoryDurable agent memory
weavz.scratchpadTemporary notes for ongoing work
weavz.webPublic web reading and extraction
weavz.httpDirect API calls

For browser work, agents should batch several browser operations inside one weavz_execute call, such as snapshot, click, type, evaluate, and screenshot, then return a concise result. Reuse sessionId across separate runs only when the workflow needs human handoff or persistent browser state.

Try It In Claude

Claude supports custom remote MCP connectors. For individual plans, use the Claude setup button above or add a custom connector from Customize > Connectors. For Team and Enterprise plans, an Owner or Primary Owner can add the connector from organization settings; members then connect it individually.

1

Open Claude setup

Click Open Claude setup in the setup panel. Claude opens the custom connector flow with the Weavz connector name and URL already filled.

2

Confirm the connector

If Claude opens connector settings without prefill, add a custom connector manually and paste https://platform.weavz.io/mcp/weavz, or your self-hosted Weavz domain plus /mcp/weavz.

3

Sign in to Weavz

Claude opens the Weavz authorization flow. Sign in, choose a workspace if prompted, and approve the connector.

4

Enable it in a chat

Enable Weavz from Claude's connector or tools menu for the conversation where the agent should use it.

For organization rollouts, add Weavz from the team connector settings and ask each member to connect their own Weavz account. Each member receives the same workspace surface, while account access stays scoped to the user where an integration requires it.

Try It In ChatGPT

ChatGPT's current custom MCP flow starts from Plugins on the web. OpenAI lists full MCP support for Business and Enterprise/Edu workspaces. Pro's read/fetch-only connections cannot provide the full Weavz offering, including write actions. Account and workspace policies control who can create or publish a connection. This setup creates a custom plugin for the permitted account or workspace; it does not place Weavz in a public directory or mean OpenAI has approved it. See OpenAI's current instructions for connecting custom MCP servers for availability and permission details.

1

Add a custom MCP server

In ChatGPT on the web, open Plugins, select +, then choose Add custom MCP server. If your account still shows the legacy Settings > Apps > Create flow, you can use that instead; follow its Scan Tools step before creating the app.

2

Enter the Weavz endpoint

Give the server a name and optional description. Under Connection, paste the public HTTPS Weavz MCP URL shown in the setup panel. Choose OAuth for authentication. In the legacy flow, select Scan Tools and complete the OAuth prompt when it appears.

3

Review and create

Read the risk warning and acknowledge it to continue, then select Create as a plugin. Review the discovered tools and details. During Weavz sign-in, choose the workspace this ChatGPT connection should use.

4

Install and test in a chat

Install the resulting plugin if prompted, start a new conversation, type @, and select the Weavz plugin. Try a low-impact task to confirm its tools are available. ChatGPT may ask for confirmation before some actions.

Workspace publication is a separate admin-controlled step; creating a custom plugin does not publish it for a workspace or list it publicly. The current OpenAI guide covers the separate workspace publishing and access controls.

Try It With Coding Agents

Coding agents that support remote HTTP MCP can use the same endpoint. Use OAuth when the client supports browser authorization.

ClientSetup
Claude CodeRun the CLI command below
CodexAdd the remote server, then run browser login
CursorAdd a remote HTTP MCP server named weavz
Generic MCP configUse the JSON shape below

Claude Code setup:

bash
claude mcp add --transport http weavz https://platform.weavz.io/mcp/weavz
claude mcp list

Codex CLI setup:

bash
codex mcp add weavz --url https://platform.weavz.io/mcp/weavz
codex mcp login weavz

Manual Codex config:

toml
[mcp_servers.weavz]
url = "https://platform.weavz.io/mcp/weavz"

Generic MCP config shape:

json
{
  "mcpServers": {
    "weavz": {
      "type": "http",
      "url": "https://platform.weavz.io/mcp/weavz"
    }
  }
}

Connect Integrations Inside The App

After the connector is authorized in a client with MCP app UI support, ask the AI client to open Weavz, or call the app's visible entrypoint from the client tools menu. The embedded app shows:

AreaWhat it does
IntegrationsLists configured workspace integration aliases, connection state, and available connect actions
AddSearches the Weavz app catalog and adds a new alias to the connector workspace
Agent SurfaceShows the MCP tool count and pending approval count
Connect buttonsOpens a hosted connection flow for integrations that need user-owned credentials
Disconnect and remove actionsDisconnects the current connector user from an alias, or removes a connector-managed alias from the workspace
Approval and link cardsShows large action buttons for end-user approvals, dashboard approvals, connect links, and short-lived download URLs when the MCP client supports app UI output
Dashboard linkOpens advanced workspace, MCP server, approval, partial, billing, and admin settings

Admins can configure deeper behavior in the dashboard: workspace integration aliases, connection strategies, enabled actions, input partials, Human Gates, built-in Filesystem/State KV settings, and Sandbox policy. Changes to workspace integrations sync into the connector's MCP server.

Clients that do not render MCP app UI still get the Code Mode tools. In those clients, manage integrations and approvals from the dashboard, or use connect links returned by tools when the client supports opening links.

Aliases are what agents call. Use purpose-readable names such as office_slack, support_slack_bot, customer_gmail, or billing_stripe; avoid vague names like default, prod, or slack2 when a workspace may contain more than one configured account.

Integrations added from the Weavz MCP App create a workspace integration alias, while the connected account belongs to the signed-in connector user. This keeps one user's Slack, Gmail, Sheets, or other account separate from another user's account even when they share the same workspace playbook. Built-in Filesystem, State KV, and Code Mode state created through the connector follow the same user-owned model. Use the dashboard, SDK, or API when you intentionally want a shared workspace credential or shared workspace state.

Workspace Selection

Workspace selection is intentionally part of the authorization flow.

  • A connector token is scoped to one selected workspace.
  • A user with more than one workspace chooses during sign-in.
  • A user with one workspace skips the chooser.
  • A user with no workspace receives a starter workspace.
  • To change workspaces, disconnect or reauthorize the connector and choose again.

This keeps tool execution, connection resolution, approvals, and built-in state tied to the selected workspace instead of letting a running chat silently switch context.

Launch Checklist

Before inviting users or submitting the connector to a marketplace:

  1. Confirm the connector URL is public, HTTPS, and stable.
  2. Verify sign-in works for new users, existing single-workspace users, and existing multi-workspace users.
  3. Connect at least one OAuth integration from the embedded app.
  4. Confirm Code Mode tools return expected results from the selected workspace.
  5. Test a Human Gate approval from the MCP client.
  6. Reconnect an OAuth integration and confirm the connected account updates for that user.
  7. Review tool names, descriptions, and workspace integration aliases for clarity.
  8. Confirm destructive or sensitive actions have Human Gates or are not enabled.
  9. Test in every target client before submitting for public distribution.

Troubleshooting

SymptomCheck
The client cannot add the connectorConfirm the URL is public HTTPS and ends with /mcp/weavz
The user sees the wrong workspaceDisconnect or reauthorize the connector and choose the intended workspace during sign-in
Add + Connect says static bearer is enabledOpen the MCP server, disable static bearer under Advanced auth, then add the per-user integration again
Integrations are missingAdd workspace integrations in Weavz and refresh the connector metadata in the client
A connect button is disabledThe integration may use a fixed/shared connection or may not require external authentication
A tool call says credentials are missingConnect the integration from the embedded app or dashboard, then retry
A write action pausesReview and approve the Human Gate request, then retry the tool call