refd MCP server
Commit Sep 29, 2026Track AI search visibility, competitor mentions, and citations across platforms like ChatGPT, Perplexity, and Google AI Overviews.
Also known as emaitchess/refd
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.3.0
- Last commit
- Sep 29, 2026
- License
- MIT
What is refd MCP?
refd tracks AI search visibility, competitor mentions, and citations across platforms like ChatGPT, Perplexity, and Google AI Overviews.
Summary generated from the project's README
About refd MCP server
Monitoring how AI models discuss your brand is what refd enables for marketing teams and developers. This tool tracks visibility, mentions, citations, and rankings across platforms including ChatGPT, Perplexity, Gemini, and Google AI Overviews. It provides a way to see if your brand is being cited or if competitors are gaining more traction in AI-generated answers.
Users can access intelligence through a hosted application or by self-hosting the entire stack using Cloudflare Workers, D1, and R2. The remote MCP connector allows AI agents to interact with this data. For local setup in Cursor or VS Code, you can use a one-click installation, while headless agents can connect using personal access tokens. Standard accounts are limited to five workspaces, 25 active prompts per workspace, and three enabled AI surfaces.
What you can do with it
- 1Track brand visibility in AI answersAsk an AI agent to check how often your brand is mentioned or cited in ChatGPT and Perplexity results.
- 2Monitor competitor mentionsAnalyze which competitors are being recommended by AI search engines compared to your own brand.
- 3Audit Google AI OverviewsVerify if your website is appearing in Google AI Overviews for specific industry prompts.
- 4Automate brand reporting with agentsUse a headless AI agent with a personal access token to pull brand sentiment and citation data.
Written from the project's README. Every use case is checked against a quote from it.
How to install refd MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall refd MCP in Claude Code
$ claude mcp add --transport http refd https://api.refd.ai/mcpInstall refd MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"refd": {
"url": "https://api.refd.ai/mcp"
}
}
}Install refd MCP in VS Code
.vscode/mcp.json
{
"servers": {
"refd": {
"type": "http",
"url": "https://api.refd.ai/mcp"
}
}
}Install refd MCP in VS Code CLI
$ code --add-mcp '{"name":"refd","type":"http","url":"https://api.refd.ai/mcp"}'Install refd MCP in Codex
$ codex mcp add refd --url https://api.refd.ai/mcpInstall refd MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.refd] url = "https://api.refd.ai/mcp"
Install refd MCP in Gemini CLI
$ gemini mcp add -s user --transport http refd https://api.refd.ai/mcpInstall refd MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"refd": {
"url": "https://api.refd.ai/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableemaitchess/refd is public and reachablegithub.com/emaitchess/refd ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-29github.com/emaitchess/refd ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubrefd
Open-source AI search monitoring — track how AI answers talk about any brand: visibility, mentions, citations, and rank across ChatGPT, Perplexity, Gemini, Google AI Mode, and Google AI Overviews. Use the hosted app at refd.ai or self-host the whole stack.
A Bun-workspace monorepo of three independently deployed Cloudflare Workers: apps/api (api.refd.ai) — the Hono API, OAuth, remote MCP, daily cron, and queue consumer, holding every binding; apps/dashboard (dash.refd.ai) — the React SPA as an assets-only Worker; apps/web (refd.ai) — the static Astro public site. Shared runtime-neutral code lives in packages/core. Data via BrightData (dataset scrapers + SERP API), stored in D1 (Drizzle) with gzipped raw payloads in R2.
refd also exposes the same workspace intelligence to AI agents through a remote
MCP connector. Its default data:read scope is read-only; the optional
data:write scope adds the bounded setup lifecycle, can start one onboarding
report, and can revoke the connection with explicit confirmation. The hosted
guide lives at refd.ai/agents; the
MCP connector guide covers Claude, Claude Code, ChatGPT, generic
clients, personal access tokens for headless agents, and self-hosting setup.
One click from the guide installs it in Cursor or VS Code — or claude mcp add-json refd '{"type":"http","url":"https://api.refd.ai/mcp"}'. Headless agents use a personal access token from Settings → Personal access tokens instead of OAuth.
How it works
Accounts hold workspaces; each workspace tracks one brand — its competitors, its prompt set, its runs. A daily cron creates an idempotent run for every workspace eligible for scheduled monitoring, then fans out queue messages: one batch-snapshot trigger per dataset surface × sample (trigger → notify → fetch, with a backstop poll), plus one sync SERP call per prompt × sample for AI Overviews. Every answer is scored for every tracked entity (mentioned / cited / first-mention position), and the raw payload is archived gzipped in R2. A missing AI Overview is recorded as a valid "no AIO shown", not a failure. Run dispatch persists immutable launch plans and resumes with bounded backoff. Storage converges under queue redelivery, but BrightData has no idempotency key, so a crash after provider acceptance can repeat paid work.
Develop
bun install
bun run dev # applies local migrations, then runs all three Workers behind
# Caddy on same-site subdomains over real HTTPS
Register on the login screen (business email + password ≥ 8 chars) — your first workspace is created automatically and drops you into a resumable setup wizard: name your brand, let it draft your description from your site, pick competitors and prompts, choose engines, then watch the first report fill in live. Every AI step falls back to typing it yourself. Standard accounts can create up to five workspaces, keep up to 25 active prompts in each, and enable up to three AI surfaces. Emails in ADMIN_EMAILS have no workspace or active-prompt cap and can enable all available surfaces.
bun run dev starts Caddy (Caddyfile) fronting all three Workers on same-site subdomains — Astro at https://refdlocal.io, the dashboard at https://dash.refdlocal.io, the API at https://api.refdlocal.io (add all three to /etc/hosts as 127.0.0.1, and run caddy trust once). Real HTTPS on same-site subdomains exercises secure cross-origin cookies, CORS, OAuth redirects, and WebSocket streaming just like production. Caddy stops when dev exits.
Local secrets go in apps/api/.dev.vars (gitignored): JWT_SECRET, BRIGHTDATA_API_TOKEN, BRIGHTDATA_WEBHOOK_SECRET (optional locally; requires a publicly reachable PUBLIC_BASE_URL), ADMIN_EMAILS (comma-separated administrator and operator allowlist), and EXA_API_KEY (onboarding's competitor search, optional). Non-secret build-time origins (VITE_API_ORIGIN, PUBLIC_DASHBOARD_ORIGIN, …) are committed per environment in each app's .env.development / .env.production. Analytics is a self-hosted Umami instance shared by the public site and the dashboard, so the activation funnel can span both: the web app needs PUBLIC_UMAMI_HOST_URL, PUBLIC_UMAMI_WEBSITE_ID, and PUBLIC_ANALYTICS_HOSTNAME, and the dashboard needs the same three as VITE_* (with the same website id). Leave any of them unset and the build emits no tracker at all, which is what a self-hosted deployment wants. Onboarding also uses two bindings, not secrets — Workers AI (AI) and Browser Rendering (BROWSER) — both remote: true in apps/api/wrangler.jsonc, so local dev proxies to the real services and the account needs both enabled.
bun run check— typecheck (all workspaces) ·bun run lint/lint:fix— Biome ·bun test— unit testsbun run build— build all three Workers ·bun run deploy— build, migrate D1, then deploy all three (the self-hosted/manual path; on refd.ai, merging tomaindeploys all three Workers automatically via Cloudflare)
Git worktrees are supported out of the box with wt: wt create <name> runs the checked-in .wt/setup.sh, which installs dependencies and copies local secrets and wrangler state, so a fresh worktree behaves like your main checkout.
Self-host
wrangler queues create refd-ingest && wrangler queues create refd-ingest-dlq
wrangler secret put JWT_SECRET
wrangler secret put BRIGHTDATA_API_TOKEN
wrangler secret put ADMIN_EMAILS # comma-separated admin/operator allowlist
wrangler secret put EXA_API_KEY # optional: onboarding competitor search
bun run db:migrate:remote
bun run deploy
bun run deploy builds all three Workers and deploys them (refd-api, refd-dashboard, refd-web); point their custom domains at api., dash., and the apex. The API workspace's own deploy script runs remote D1 migrations first, so deploying @refd/api alone (CI or a Cloudflare dash deploy command) always brings the schema along. (The hosted deployment wires these deploy scripts to push-to-main via Cloudflare's Git integration, so refd.ai itself has no manual deploy step.) You'll need a Cloudflare account (Workers paid plan for Queues, plus Workers AI and Browser Rendering enabled for onboarding), a D1 database + R2 bucket (ids/names in apps/api/wrangler.jsonc), and a BrightData account: fill the dataset IDs in apps/api/wrangler.jsonc vars (dashboard → Web Scrapers → each AI scraper) and create a SERP API zone matching BRIGHTDATA_SERP_ZONE. Set the deployment origins (PUBLIC_BASE_URL, DASHBOARD_ORIGIN, PUBLIC_SITE_ORIGIN, API_ORIGIN) and SCHEDULED_MONITORING_POLICY=all for a self-hosted deployment; the checked-in entitled policy is for refd.ai and limits cron to active pilot or subscribed workspaces. Cron schedule (daily 06:00 UTC), samples, and geo also live in apps/api/wrangler.jsonc.
Notes
- AI answers are non-deterministic: hosted scheduled runs use
SAMPLES=1per prompt and surface; read trends across completed runs, not one sample. Operators can request additional samples for focused manual runs. - Each standard full run is capped at 25 active prompts × 3 enabled surfaces × samples (25 × 3 × 1 = 75 records at the default). Quota scales with the number of workspaces eligible for scheduled monitoring.
- The public site is built to be read by agents as well as people: every page is also served as markdown at the same path with
.mdappended,/llms.txtfollows the llmstxt.org format and links those markdown versions, and/llms-full.txtinlines them all. Self-hosted deployments get this for free. - Design system:
DESIGN.md. Scoring/metrics contract:docs/METRICS.md. Remote MCP + OAuth:docs/mcp.md.
Contributing
Contributions welcome. See CONTRIBUTING.md for setup and the
checks your PR must pass, and CODE_OF_CONDUCT.md for
community expectations. Found a security issue? Follow SECURITY.md
instead of opening a public issue.
License
MIT © refd
refd MCP questions
How do I add refd MCP to Claude Code?
Run claude mcp add --transport http refd https://api.refd.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add refd MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can I track with refd?
You can track how AI answers talk about any brand, including visibility, mentions, citations, and rank across ChatGPT, Perplexity, Gemini, Google AI Mode, and Google AI Overviews.
How do I use refd with AI agents?
You can use the remote MCP connector to expose workspace intelligence to AI agents. Headless agents can use a personal access token from the Settings menu.
What are the limits for standard accounts?
Standard accounts can create up to five workspaces, maintain up to 25 active prompts per workspace, and enable up to three AI surfaces.