Solutions

Context your AI agents can be trusted with.

One governed MCP gateway feeds Claude, ChatGPT, coding agents, and your own AI infrastructure the same permission-aware knowledge.

ClaudeMCP CLIENT

ACTING FORalex@yourco · customers

tool callsearch("data retention policy")

◇ Identity⌘ Groups✓ Permissionschecked before retrieval

✓

Data retention policyPAGE · CUSTOMERS MAY READ

✓

Security overviewPAGE · PUBLIC

Internal legal notesNOT PERMITTED · NEVER RETRIEVED

What platform teams do with GraphStaff

Stop pasting context into prompts.

Publish one gateway

Every AI agent connects to the same MCP server instead of a per-team scrape.

Enforce permissions in retrieval

Tool calls carry the reader's groups, so AI agents receive only permitted content.

Stay model-independent

Swap the model or the AI agent. The knowledge layer does not change.

Update once

Fix the page and every AI agent answers correctly on the next call.

Policy-checked retrieval

The access decision travels with the answer.

The policy engine that gates the website gates retrieval, so an AI agent acting for Alex sees exactly what Alex sees.

Frequently asked questions.

The short version of what teams usually want to know before they see GraphStaff in action.

Which AI agents can connect?

Anything that speaks Model Context Protocol: Claude, ChatGPT, Cursor, and custom agents.

Is this Company Brain?

Company Brain is the product built on this capability for internal company knowledge, rolled out one customer at a time with dedicated implementation.

Can AI agents write through the gateway?

No. The MCP server is read-only by design.

What does it cost?

Documentation and knowledge-hub surfaces are included in the $500 per month plan. Company Brain starts at $80,000 per year on a one-year contract.

See it with your knowledge

AI agents are only as good as their context.

Tell us which AI agents your teams run. We will show them answering from one governed source.