fulcru
Get named by AI search engines.
When someone asks ChatGPT "what's the best CRM for a small team", the answer namestwo or three products. Those get the customer. Everyone else is invisible.
fulcru finds the questions where an AI assistant names a competitor instead ofyou, writes the page that closes the gap, and measures what publishing it did. Itruns as a CLI, an MCP server, and an agent skill, so a human or an agent can runthe whole loop.
This repo is the open, self-hostable agent surface. The measurement engine is thehosted Fulcru service; everything here is a thin client thattalks to it with your token.
We run it on ourselves and publish the result, whichever way it goes. Today itscores us 0 out of 34 prompts: we sell AI visibility and we score zero on ourown product, with thefull run and the source data.
npm install -g fulcru
export FULCRU_TOKEN=pk_... # Settings -> Integrations at fulcru.app
Or run it in Docker, with nothing installed on the host:
docker build -t fulcru .
docker run --rm -e FULCRU_TOKEN=pk_... fulcru gaps
No secrets are baked into the image; the token is passed at run time. Verified onnode:20-alpine, 2026-07-27.
The loop
$ fulcru gaps
0% k57jc... best AI visibility tracker for a SaaS startup -> AI names Profound, Peec AI
0% k57bw... how do I know if ChatGPT recommends my brand -> AI names Otterly AI
33% k57xz... tools to track brand mentions in Perplexity -> AI names Semrush
Write the top one: fulcru write k57jc...
$ fulcru write k57jc... > page.md # the drafted article, grounded in what AI cites
$ fulcru publish k57jc... https://mysite.com/blog/ai-visibility-trackers
Published. Baseline: AI names you in 0% of 9 measured answers.
$ fulcru delta
0% -> 44% +44pts Best AI Visibility Trackers, Compared
That last line is the whole point.
Commands
| Command | What it does |
|---|---|
fulcru gaps [n] |
Questions where AI names a competitor and not you, worst first |
fulcru write <promptId> |
Writes the page that closes one gap; Markdown to stdout |
fulcru publish <pageId> <url> |
Marks it live and snapshots the baseline to measure from |
fulcru delta |
What your published pages actually did |
fulcru report [section] |
overview, competitors, sources, mentions, prompts |
Add --json to any command for the raw payload.
Built for agents
Output is terse lines, not JSON blobs, because the caller is usually an LLM andits context is the scarce resource. fulcru gaps costs an agent about 50 tokens;the same data as raw API JSON costs about 800. fulcru write sends the Markdownto stdout and everything else to stderr, so fulcru write <id> > page.md gives aclean file.
MCP
Two ways to wire the five Fulcru tools into an agent.
Remote (hosted). Point any MCP client at the hosted endpoint with your token:
{
"mcpServers": {
"fulcru": {
"url": "https://little-orca-977.convex.site/mcp",
"headers": { "Authorization": "Bearer pk_..." }
}
}
}
Local (stdio). For hosts that prefer a subprocess, this package ships a stdioMCP server that proxies to the hosted endpoint:
{
"mcpServers": {
"fulcru": {
"command": "npx",
"args": ["-y", "-p", "fulcru", "fulcru-mcp"],
"env": { "FULCRU_TOKEN": "pk_..." }
}
}
}
The -p is not decoration. This package ships two commands, and without it npxruns the one named after the package, which is the CLI: the host gets a usagescreen instead of an MCP server.
Tools: fulcru_gaps, fulcru_write_page, fulcru_publish_page, fulcru_delta,fulcru_visibility.
Both speak protocol revision 2026-07-28 and the older handshake-basedrevisions, and pick per request from what the client sends. A client on the newrevision gets server/discover, per-request _meta, and a cacheable tool list;one still sending initialize is served exactly as before. Nothing needsconfiguring either way.
Skill
The skills/fulcru skill runs the whole playbook usingnothing but web access — audit a domain, find the gaps, write the page, re-measure— with no account and no token. Install it into an agent that supports skills:
# Claude / OpenClaw
npx skills add gsmmediaro/fulcru
# Hermes
hermes skills install gsmmediaro/fulcru
Hermes scans third-party skills before installing and prints the verdict, so youcan see what you are agreeing to run. If you would rather track this repo as asource and pick up updates, tap it instead:
hermes skills tap add gsmmediaro/fulcru
hermes skills install fulcru
The CLI and MCP above are what you use when you want it measured continuouslyacross every engine, with the before/after delta tracked for you.
Configuration
| Env var | Required | Default | Purpose |
|---|---|---|---|
FULCRU_TOKEN |
for the CLI + local MCP | — | Your account token (Settings -> Integrations) |
FULCRU_ENDPOINT |
no | https://little-orca-977.convex.site/mcp |
Point at a self-hosted or custom-domain endpoint |
No secrets are baked into this repo. The token is read from the environment only.
Self-hosting
The skill needs nothing. The CLI and MCP need a Fulcru account for the continuous,measured loop; point FULCRU_ENDPOINT at your own instance if you run one.
A Docker image is provided:
docker build -t fulcru .
docker run --rm -e FULCRU_TOKEN=pk_... fulcru gaps
Contributing
Issues and PRs welcome. The tool logic lives in the hosted service; this repo isthe CLI, the stdio MCP proxy, and the skill. If AI names a competitor instead ofyou, open an issue with the question — that is exactly the gap this is built toclose.
If this is useful, a ⭐ genuinely helps.
License
AGPL-3.0-or-later. See LICENSE.