WeWeb
by WeWeb
Build and edit a WeWeb no-code app from an AI agent. Anthropic lists 125 tools — 42 read, 63 write, 20 destructive — against your live project. OAuth sign-in grants one scope, mcp:write, with no read-only option.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Connect WeWeb via MCP
https://ai-api.weweb.io/v1/mcpWorks in any MCP-compatible client. In Agentman Studio it is one click — no config file to edit.
WeWeb Tools & Capabilities (125)
Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.
Limits
- One OAuth scope, and it is a wildcard. The RFC 9728 resource descriptor at
https://ai-api.weweb.io/.well-known/oauth-protected-resourceand the authorization server metadata athttps://api.weweb.io/.well-known/oauth-authorization-serverboth advertise exactly["mcp:write"], checked 2026-08-23. The boundary does not fall between the routine write and the irreversible one — the same grant that lets an agent rename a page lets it drop a table. There is no read-only mode to hand a research agent. - 125 tools is more than most clients will surface well. Every tool description competes for the same context window, and the practical control is per-tool permissioning in the client, not anything the server offers.
- WeWeb calls this beta, in its own words. Its documentation states MCP is "currently in beta", that calls "run against your real project", and recommends a non-critical project. WeWeb AI, the in-editor sibling, carries a separate beta warning.
- Twenty destructive tools, three of them schema-level.
dropWeWebTable,dropWeWebTableColumnanddropWeWebTableConstraintdestroy structure and the data inside it. Editor Backups restore an editor version, which we found no documentation extending to dropped backend tables. - Plugin actions are out of scope, by WeWeb's own statement, and the documented workaround is explicitly unofficial.
- We could not read tool schemas or safety annotations. The endpoint returned 401 to an anonymous request on 2026-08-23, so no parameter-level detail is published here and no
readOnlyHintis available to check our classification against. - Neither tool list is authoritative. The directory holds 24 names WeWeb's table omits, four of them destructive; WeWeb's table holds four names the directory omits, two of them writes. Both drifted, in opposite directions.
- Whether integration tools expose stored credentials is unresolved. WeWeb documents that integration connections hold API keys, and the connector has five integration tools. We found no documentation stating what those tools return, and we did not test it.
- No prompts or resources could be checked. The server requires authentication before
initializecompletes, so its declared capabilities were never visible to us. Anthropic's directory lists zero prompt names.
Frequently asked questions
No. No tool among the 125 publishes or deploys anything to a live site. WeWeb documents publishing as an editor action: you click Publish in the top right, choose Publish your app, then Publish to production or Publish to staging. The one publish-named tool, publishComponent, publishes a reusable component into your project library, which is an editor asset rather than a live site.
It edits the editor version, not the published one. WeWeb states that publishing takes the latest version of your project and makes it available outside the editor, so tool calls change what your next publish will contain rather than what visitors see now. WeWeb's own beta warning says tool calls run against your real project and can create, edit, or delete resources.
Twenty of the 125, by name. Seventeen carry a delete verb and three carry drop: dropWeWebTable, dropWeWebTableColumn and dropWeWebTableConstraint. Dropping a table is a schema-level destruction of stored rows, and WeWeb documents no undo for it. Editor Backups roll back the editor version of a project, which is a different thing from restoring backend table data.
Yes, all four operations. listAllEnvVariables, createEnvVariable, editEnvVariable and deleteEnvVariable are in Anthropic's listing and in WeWeb's own documented tool table. WeWeb does not publish whether the list tool returns variable values or only their names, so assume any secret stored as a WeWeb environment variable is reachable by a connected agent.
Exactly one, and it is a wildcard. WeWeb's RFC 9728 resource descriptor and its authorization server both advertise scopes_supported of mcp:write, checked live on 2026-08-23. There is no read-only counterpart, so consent cannot separate listing your projects from dropping a table. Granting the connector grants everything the server implements, now and later.
Pro or Partner for ongoing use. WeWeb's pricing documentation states the MCP server is available on a 14-day trial on the Free and Essential seat plans, and that Pro and Partner seat plans include ongoing access. When the trial ends without an upgrade, WeWeb states your AI client can no longer call WeWeb tools through MCP.
Yes, through table views. WeWeb documents that a view of a table carries permissions set to Public, Authenticated, or specific Roles and Groups. createTableView and updateTableView are among the 125 tools, so an agent editing a view is editing the access boundary. Nothing in the tool names distinguishes a cosmetic view edit from a permission change.
WeWeb states the MCP does not expose ways for AI to build using plugin actions. Its documentation recommends switching Xano and Supabase to the newer Integrations, whose actions the MCP can reach. WeWeb also documents a makeshift workaround where you paste workflow JSON between the editor and your agent, and explicitly labels it not an official MCP feature.
Sources
- WeWeb MCP documentation, "Intro to WeWeb MCP" (retrieved 2026-08-23). Source of the vendor tool table, the plugin exclusion, the beta warning and the supported-client list.
docs.weweb.io/robots.txtisAllow: /with no Content-Signal directive. · retrieved 2026-08-23 - WeWeb documentation, "Publishing your application" (retrieved 2026-08-23) · retrieved 2026-08-23
- WeWeb documentation, "Understanding WeWeb pricing" (retrieved 2026-08-23). Source of the MCP plan gate. · retrieved 2026-08-23
- WeWeb documentation, "Securing your application" (retrieved 2026-08-23). Source of the table-view permission model. · retrieved 2026-08-23
- WeWeb documentation, "Integrations" (retrieved 2026-08-23). Source of the credential-storing connection model. · retrieved 2026-08-23
- WeWeb documentation, "Intro to components" and "Library overview" — · (retrieved 2026-08-23) · retrieved 2026-08-23
- WeWeb documentation index,
llms.txt(retrieved 2026-08-23). It indexes 300+ pages but names no MCP page, andllms-full.txtreturns 404. · retrieved 2026-08-23 - Live auth posture check, 2026-08-23: anonymous
initializetohttps://ai-api.weweb.io/v1/mcpreturned HTTP 401 withWWW-Authenticate: Bearer resource_metadata="https://ai-api.weweb.io/.well-known/oauth-protected-resource"; that descriptor andhttps://api.weweb.io/.well-known/oauth-authorization-serverboth returnedscopes_supported: ["mcp:write"]· retrieved 2026-08-23 - Anthropic Connectors Directory entry — , read from our directory snapshot dated 2026-08-23 · retrieved 2026-08-23
- WeWeb support — · Privacy
Use in Agentman
Connect once and your agents call these tools on their own — on a schedule, in a workflow, with nobody at the keyboard.
Open in Agentman StudioServer Info
- Category
- Developer Tools
- Developer
- WeWeb
- Tools
- 125
- Domain
- ai-api.weweb.io
Using Claude Desktop or another MCP client? Setup docs — the connection URL above works anywhere.