Build on Shruwd

MCP server

The Shruwd MCP server: hosted at https://shruwd.io/mcp for Claude, ChatGPT and Grok, or local over npx for Claude Desktop, Claude Code and Cursor.

The Shruwd MCP server gives an AI assistant tools to set up a brand, add prompts and competitors, read how the brand appears in AI answers, and act on findings. It runs two ways, with the same tools:

Hosted at https://shruwd.io/mcp. Add it to Claude, ChatGPT or Grok and sign in with your Shruwd account. No key.
Local, as the shruwd-mcp npm package, with an API key.

The same install and configuration are published as JSON at /.well-known/mcp.json.

Hosted


URL	`https://shruwd.io/mcp`
Transport	Streamable HTTP
Sign-in	Shruwd sign-in (OAuth), or an API key as `Authorization: Bearer sh_live_…`

Signing in connects the app to one workspace. It reaches your brands there, with your role on each and the access you choose: read only, or read and write. Disconnect it any time under Account → Connected apps.

Step by step: Claude · ChatGPT · Grok.

Claude Code

bash

claude mcp add --transport http shruwd https://shruwd.io/mcp

Then run /mcp in Claude Code and sign in. To use a key instead:

bash

claude mcp add --transport http shruwd https://shruwd.io/mcp --header "Authorization: Bearer sh_live_…"

Local

shruwd-mcp runs on your machine over stdio and talks to the API with your key.

Prerequisites

An API key from Account → API keys. A key is bound to one workspace and reaches your brands in it, with your role on each: reads need viewer, writes editor, minting an ingest token admin, and creating or archiving a brand the owner. To work across several workspaces, mint a key in each and add one server entry per workspace. See Roles.

Claude Desktop

In claude_desktop_config.json:

json

{
  "mcpServers": {
    "shruwd": {
      "command": "npx",
      "args": ["-y", "shruwd-mcp"],
      "env": { "SHRUWD_API_KEY": "sh_live_…" }
    }
  }
}

Claude Code

bash

claude mcp add shruwd -e SHRUWD_API_KEY=sh_live_… -- npx -y shruwd-mcp

Cursor

In .cursor/mcp.json:

json

{
  "mcpServers": {
    "shruwd": {
      "command": "npx",
      "args": ["-y", "shruwd-mcp"],
      "env": { "SHRUWD_API_KEY": "sh_live_…" }
    }
  }
}

Environment

Variable
`SHRUWD_API_KEY`	Required
`SHRUWD_API_URL`	Optional. Defaults to `https://shruwd.io/api/v1`

Tools

Tool	Does
`shruwd_get_workspace`	Plan, entitlements, usage, brands. Start here
`shruwd_list_brands` · `shruwd_get_brand` · `shruwd_create_brand` · `shruwd_update_brand` · `shruwd_archive_brand`	Brands. Creating one also creates its self entity and first measurement. Creating and archiving need `owner`
`shruwd_list_prompts` · `shruwd_add_prompts` · `shruwd_update_prompt` · `shruwd_remove_prompt`	The questions asked of each engine every cycle
`shruwd_list_entities` · `shruwd_add_competitor` · `shruwd_set_entity` · `shruwd_remove_entity`	The brand and its competitors, with the exact aliases that count
`shruwd_run_measurement` · `shruwd_list_cycles`	Measure now; watch the cycle
`shruwd_get_visibility` · `shruwd_get_visibility_series` · `shruwd_get_crawlers`	Mention rate and share of voice with intervals, and verified crawler activity
`shruwd_list_crawler_paths`	Which paths each crawler fetched and what it got: where a bot's errors came from
`shruwd_list_sources`	Which sites and pages the answers cite, and whose they are, for every question or one
`shruwd_list_answers`	The latest individual answers, for one prompt or engine if you ask. Evidence, not a metric
`shruwd_list_suggestions` · `shruwd_accept_suggestion` · `shruwd_dismiss_suggestion`	Competitors the answers named that you do not track
`shruwd_suggest_setup`	Drafts prompts and competitors from your homepage. Nothing is saved
`shruwd_list_findings` · `shruwd_get_finding` · `shruwd_transition_finding`	Diagnoses with a specific fix; mark one applied to start the recheck. Capped plans count the rest in `locked`
`shruwd_create_ingest_token`	The token and endpoint for shipping server logs. Needs `admin`

Tools that change something are marked so, and the ones that remove something as destructive, so an app can ask you before it calls them. Archiving a brand and removing a prompt or competitor never delete history.

What the tools will not do

No tool computes anything the API does not return. The server is a transport, and every guarantee the API keeps, it keeps:

A metric is never a bare number. Each carries its 95% interval and n, or an explicit insufficient_data — which the tool descriptions tell the agent not to read as zero.
No tool can mark a finding resolved. resolved and not_moved belong to the recheck. An agent can acknowledge, apply or dismiss; it cannot declare success.
Nothing is saved without you. shruwd_suggest_setup drafts prompts and competitors and saves none of them — they go in through the normal tools, with the same checks as adding them by hand.
A capped plan hides nothing silently. Where your plan shows only its top findings, shruwd_list_findings returns those and counts the rest in locked by severity, so the agent is told they exist rather than reporting a short list as the whole set. Fetching a locked one is 403 not_entitled.

Next steps

Use Shruwd in Claude, ChatGPT or Grok
For AI agents — the docs themselves, machine-readable
TypeScript SDK — the client underneath these tools