The agent-native org brain
Stage any externally-originated artifact — a Slack thread, an email, a review, a note — into a per-org knowledge layer that's searchable in seconds and promotable into a structured wiki on demand. One status call returns counts, the most recent captured sources and wiki entities, and a 7-day event feed so an agent can answer 'what does our brain know about us?' in a single round-trip.
How it works
From a raw artifact to a structured, queryable org brain 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/brain 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.
Stage a source
Call `wiki_stage_source` with a canonical `source_uri` (e.g. `slack://C0123456789/1700000000.000000`), a caller-provided `slug`, a `source_type`, a `title`, and the source body as markdown. The server writes it to S3, kicks off async vectorization, and emits a `source_staged` brain event — searchable via `search_knowledge` in ~10–60s. Free.
Promote into the wiki
When a captured source is worth folding into the structured wiki, call `wiki_ingest_source` with the same `source_uri` and a wiki scope (`{ kind: 'org' }` or `{ kind: 'idea', ideaSlug }`). The server resolves the staged S3 key, runs the wiki synthesis path, updates entity pages and the index, appends a log entry, and returns clickable wiki links to surface back to the user. Idempotent — re-promoting updates in place.
Read the snapshot
`brain_status_snapshot` returns the current state of the org brain in one call — counts of captured sources, knowledge chunks, wiki entities, and wiki notes; the 10 most recently captured sources and 10 most recently updated wiki entities; and the last 7 days of brain events as a chronological feed (capped at 100). Free. Powers the Brain dashboard panel and lets an agent answer 'what does the brain know?' in one round-trip.
Available tools
4 tools your AI agent can call through the Model Context Protocol.
brain_status_snapshot
Aggregate the current Brain state for the org in one read-through call.
wiki_ingest_source
Promote a previously-staged source (captured via wiki_stage_source) into the wiki by its canonical source_uri.
wiki_stage_source
Stage an externally-originated source artifact into the brain.
wiki_unstage_source
Soft-delete a previously-staged source by its canonical source_uri.
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-brain \
--transport http \
https://mcp.gentic.co/brain \
--header "Authorization: Bearer YOUR_API_KEY"You can also connect via OAuth — just add gentic-brain 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.
Transparent per-call pricing
Staging, unstaging, and the status snapshot are free. Wiki promotion is 25¢ per call — pay only when a captured source becomes a permanent wiki entity.
| Tool | Cost |
|---|---|
| brain_status_snapshot | Free |
| wiki_ingest_source | 25¢ / call |
| wiki_stage_source | Free |
| wiki_unstage_source | Free |
Pricing is pulled live from the Gentic MCP manifest so it always matches what you'll actually be charged.
Why agent-native?
Traditional capture pipelines assume a human filling in fields. The brain assumes an agent depositing through one mandated ingest path — and a human reading the result.
Identity-first
Every primitive — stage, promote, unstage — identifies sources by canonical `source_uri`. The caller never juggles slugs across calls; re-staging the same URI overwrites in place and emits a `source_restaged` event. Slack reactions, future doc connectors, and direct uploads all deposit through the same path.
Async by default
`wiki_stage_source` writes to S3 synchronously and chains vectorization in the background. The agent gets a response in milliseconds; the knowledge chunks become searchable via `search_knowledge` in ~10–60s. No blocking, no long-running tool calls.
Wiki on demand
Capture isn't promotion. A staged source is searchable knowledge — promote it into the structured wiki only when it's worth a permanent entity page. `wiki_ingest_source` is the bridge, and the response includes clickable wiki paths so the agent can show its work.
Free to read, 25¢ to promote
Staging, unstaging, and the status snapshot are free. Wiki promotion is 25¢ per call — you only pay when a captured source becomes a permanent wiki entity. Vectorization charges its own per-chunk meter on completion.