Chrysent Axis Knowledge Base
Design-partner previewAvailable to design partners. Connector ingestion and permission-aware retrieval are exposed in the preview.Permission-aware retrieval across your organizational knowledge — for humans and AI agents, with the access controls you already operate.
The problem this solves
Your institutional knowledge is fragmented across wikis, document stores, databases, and project systems. AI assistants cannot retrieve it safely, and humans cannot find it fast.
You need a retrieval layer that respects the access controls you already operate, surfaces the right context, and lets you audit what left and what did not.
What changes when you adopt Axis Knowledge Base
Permission-aware retrieval
Map permissions from Okta, LDAP, Active Directory, or your IdP. Departments and teams only retrieve what their role allows.
Connectors for structured and unstructured sources
Ingest from documents, query formats, databases, blob storage, and push-based pipelines.
MCP-accessible
External harnesses consume Axis Knowledge Base through MCP with OAuth or SAML authentication.
How Axis Knowledge Base operates
- 01
Connect sources
Ingest via connectors, queries, or push. Sources are tagged with tenant and permission scope.
- 02
Map permissions
Pull group membership from your IdP so retrieval respects existing access boundaries.
- 03
Serve via MCP or chat UI
Humans and AI agents consume the same retrieval layer; audit logs show exactly what was returned and to whom.
Component map
- ConnectorsStructured and unstructured source ingestion.
- Identity bridgeMaps IdP groups to retrieval scope.
- MCP serverStandardized interface for AI agents and external harnesses.
For the full platform architecture, see /platform.
Who uses it and how
Knowledge management
Scenario: You want to consolidate internal docs and project history behind one retrieval surface.
Gain: Connectors plus identity-aware retrieval, with audit on every access.
AI platform engineering
Scenario: You want to give AI agents context without exposing confidential material.
Gain: Permission-aware retrieval that inherits your existing access model.
See the product surface
Product screenshots and a short demo walkthrough are available to design partners under NDA. Request access below to receive the latest captures and a recorded session.
Request access →Supported systems
Chrysent Axis Knowledge Base integrates with the providers and frameworks below. Each entry shows the current support status. Documentation for the full integration list is coming soon.
- SAML 2.0Tech Preview
- OAuth 2.0Tech Preview
- Confluence, Google Drive connectorsTech Preview
Where it runs and how data is handled
Chrysent sells self-hosted software only. Software and retained product data remain in customer-owned or customer-controlled infrastructure. Customer-configured external model providers receive provider-bound request data under the customer's provider agreement. This model supports data sovereignty and residency requirements. Data handling and retention are described on the Data handling & deployment page. Security architecture, encryption, and incident response are documented on Security & trust.
Benchmark and evaluation methodology
The first public benchmark study is in preparation. Until it ships, design partners can request the evaluation methodology and a private run report under NDA via the contact form.
Other Chrysent products
Common questions
How are permissions enforced?
Retrieval runs against the connector permission model. The Chrysent session ledger records what was returned and to whom.
Can AI agents use this directly?
Yes. The MCP server exposes Axis Knowledge Base to any compatible agent with OAuth or SAML authentication.