The agent-native content writer
Give your AI agent your brand's voice. Feed it your existing writing, and the Content server builds a writing profile — a stylometric fingerprint, your brand lexicon, and an anti-slop calibration — then generates on-brand drafts from a brief, scored against that profile with a checkable scorecard. Learn the voice, build the profile, write the draft — all through the Model Context Protocol.
How it works
From a folder of your best writing to on-brand drafts in five steps.
Sign up and get an API key
Create a free account at gentic.co, generate an API key from your dashboard, and use it as a Bearer token to authenticate your agent.
Add the MCP server to your agent
Drop https://mcp.gentic.co/content into Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, or any MCP-compatible client. Pass your Gentic API key as a Bearer token — or connect via OAuth on clients that support it.
Feed it your existing writing
Add samples of the brand's real content — paste the text or point it at a URL. Tag each with a content type (blog, email, newsletter…) and approve the extraction. This corpus is the ground truth the profile is built from.
Build the writing profile
Build a profile for one voice + content type. It runs anti-slop-first — filters your corpus to the slop-free subset, then computes the stylometric fingerprint, your brand lexicon, and the on-voice calibration from that subset. This becomes the objective scorer.
Generate on-brand drafts, with a receipt
Give it a brief. The writer generates candidates, ranks by stylometric fit, and gates on a two-family on-voice panel plus anti-slop, near-copy, and factuality — then returns the draft with a checkable scorecard and a ship decision.
Available tools
7 tools your AI agent can call through the Model Context Protocol.
add_content_sample
Add a piece of the brand's existing writing to the content corpus (used to build the writing profile).
approve_content_sample
Approve a captured content sample's extraction (from add_content_sample) so it becomes eligible to build a writing profile.
build_writing_profile
Build (or rebuild) the brand's writing profile for one voice + content type — async.
create_content
Generate an on-brand draft from a brief, scored against the brand's writing profile — async.
get_content_jobs
Poll a Content job by id (profile build or content generation).
get_writing_profile
Get the brand's built writing profile (the objective scorer: stylometric fingerprint band + brand lexicon + on-voice judge threshold + anti-slop clean-subset provenance).
list_content_samples
List the brand content samples in the corpus (from add_content_sample) — id, content_type, title, source, word_count, and whether each is eligible (approved) for profiling.
Connect in seconds
Sign up, grab your API key, and add the MCP server to your agent. Works with Claude Code, Claude Web, OpenClaw, Claude Cowork, ChatGPT, n8n, and any MCP client.
claude mcp add gentic-content \
--transport http \
https://mcp.gentic.co/content \
--header "Authorization: Bearer YOUR_API_KEY"You can also connect via OAuth — just add gentic-content as a connector in Claude or ChatGPT settings. No API key needed; authentication is handled automatically.
Install the Gentic agent skill to teach your agent the optimal workflow so it gets the best results automatically.
npx skills add gentic-co/agent-skillsWorks with Claude Code, Cursor, Copilot, and 40+ other agents.
Pay per result, not per seat
Building a writing profile is $2.00, and each shipped draft is $0.50. Adding samples, reading profiles, and polling jobs are all free. No monthly platform fee.
| Tool | Cost |
|---|---|
| add_content_sample | Free |
| approve_content_sample | Free |
| build_writing_profile | 200¢ / result |
| create_content | 50¢ / result |
| get_content_jobs | Free |
| get_writing_profile | Free |
| list_content_samples | Free |
Pricing is pulled live from the Gentic MCP manifest so it always matches what you'll actually be charged.
Why an agent-native content writer?
Generic LLM writing sounds like everyone else's. This one learns your brand's actual voice from your actual writing, and hands your agent an objective way to check every draft against it.
Your voice, measured
The profile is a stylometric fingerprint plus your brand lexicon — not a vibe. Drafts are scored against it, so 'on-brand' becomes something you can actually check.
Anti-slop by design
The profile is built from the slop-free subset of your corpus, and every draft is gated on anti-slop, near-copy, and factuality before it ships. No generic AI mush.
Composable workflows
Chain content generation with research, reviews, your CMS, or a publishing step. Build end-to-end content pipelines your way — the scorecard travels with the draft.
Pay per result
No monthly seats or platform fees. You pay only when a profile is built or a draft ships — reading samples, profiles, and job status is free.