Shruwd Mcp

io.github.ilprPublished by GitHub account ilprv0.1.11Updated Nov 3, 2026

Set up a brand, read its AI-search visibility, and act on diagnostic findings.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Shruwd MCP lets an assistant set up a brand, track prompts and competitors, and read how the brand appears in AI-generated answers.

What you can do
  • Read workspace plan, entitlements, usage and brands
  • Create, update, list and archive brands, and manage the prompts asked of each AI engine
  • Manage the brand and competitor entities with the aliases that count as mentions
  • Run measurements, list cycles, and read visibility, share of voice and crawler activity
  • Inspect cited sources, individual answers, and diagnostic findings with fixes
  • Draft suggested prompts and competitors, and create an ingest token for server logs
When to use it
Useful when you want an assistant to set up or maintain a brand's AI-search visibility tracking, review which prompts and competitors are monitored, and work through diagnostic findings without opening the dashboard.
Requirements
Either the hosted endpoint at shruwd.io/mcp with an OAuth sign-in, or the local npm package shruwd-mcp run via npx with Node.js. A Shruwd account and an API key from the dashboard, supplied as SHRUWD_API_KEY; SHRUWD_API_URL optionally overrides the API base URL. Network access to Shruwd.
Before you install
The API key is a secret bound to one workspace and acts with your role on each brand; writes need editor, ingest token creation needs admin, and creating or archiving a brand needs owner. Tools create, update, archive and remove brands, prompts and entities, and start measurements. Brand setup data is sent to Shruwd.

Installation

In SourceWeft

  1. Open Shruwd Mcp in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ilpr%2Fshruwd-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "shruwd": {
      "type": "http",
      "url": "https://shruwd.io/mcp"
    }
  }
}

README

shruwd-mcp

A local MCP server for Shruwd. It lets an AI agent — Claude Desktop, Claude Code, Cursor, anything that speaks MCP — set up a brand, add the prompts and competitors to track, read how the brand appears in AI-generated answers, and act on the diagnostic findings.

You need an API key from the Shruwd dashboard (Account → API keys). The key is bound to one workspace and reaches your brands in it: every brand if you own the workspace, the brands you are a member of otherwise. It acts with your role on each brand: reads need viewer, writes editor, minting an ingest token admin; creating or archiving a brand needs the owner. To work across several workspaces, mint a key in each and add one server entry per workspace.

Hosted, no install

The same tools run at https://shruwd.io/mcp (Streamable HTTP). In Claude.ai, ChatGPT or Grok, add that URL as a custom connector and sign in with your Shruwd account; no key needed. A client that takes a header can send a key instead:

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

Setup for each app: shruwd.io/docs/api/mcp-server.

Claude Desktop

claude_desktop_config.json:

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

Claude Code

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

Cursor

.cursor/mcp.json:

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

Tools

ToolDoes
shruwd_get_workspacePlan, entitlements, usage, brands. Start here.
shruwd_list_brands · shruwd_get_brand · shruwd_create_brand · shruwd_update_brand · shruwd_archive_brandBrands. 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_promptThe questions asked of each engine every cycle, and the page on your site that should answer each.
shruwd_list_entities · shruwd_add_competitor · shruwd_set_entity · shruwd_remove_entityThe brand and its competitors, with the exact aliases that count as a mention.
shruwd_run_measurement · shruwd_list_cyclesMeasure now; watch the cycle. Results arrive over the following hours.
shruwd_get_visibility · shruwd_get_visibility_series · shruwd_get_crawlersMention rate and share of voice with intervals, now and at every cycle close; verified AI-crawler activity.
shruwd_list_crawler_pathsWhich paths each crawler fetched and what it got: where a bot's errors came from.
shruwd_list_sourcesWhich sites and pages the answers cite, and whose they are, for every question or one.
shruwd_list_answersThe latest individual answers: whether the brand was named and at what rank, the competitors named, the pages cited. Narrows to one prompt (a finding's subjectRef) or one engine. Evidence, not a metric.
shruwd_list_suggestions · shruwd_accept_suggestion · shruwd_dismiss_suggestionCompetitors the answers named that the brand does not track yet.
shruwd_suggest_setupDrafts 10 to 25 prompts, each with the page that should answer it, and up to six competitors from the homepage and sitemap. Nothing is saved until they are added with the usual tools.
shruwd_list_findings · shruwd_get_finding · shruwd_transition_findingDiagnoses with a specific fix; mark a fix applied to start the recheck. Capped plans return the rest as a locked count.
shruwd_create_ingest_tokenThe token and endpoint for shipping server logs. Needs admin.

Every tool returns exactly what the API returns. Metrics are never bare numbers: each is a point estimate with its 95% interval and n, or an explicit insufficient_data state, which the tool descriptions tell the agent not to read as zero. Plans that cap visible findings report the remainder as a locked count rather than hiding that it exists.

Environment

Variable
SHRUWD_API_KEYRequired.
SHRUWD_API_URLOptional. Defaults to https://shruwd.io/api/v1.

Source: README.md at commit cb42186

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

7
  1. v0.1.11LatestNov 3, 2026
  2. v0.1.9Oct 19, 2026
  3. v0.1.8Oct 15, 2026
  4. v0.1.7Oct 15, 2026
  5. v0.1.6Sep 30, 2026
  6. v0.1.5Sep 22, 2026
  7. v0.1.2Sep 20, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts