Which AI clients can connect to Plexara?

Any client that speaks the Model Context Protocol. That includes Claude Desktop, ChatGPT, the Anthropic and OpenAI SDKs, Cursor, Continue, and custom agents you build in-house. Plexara is the server; the client is your choice.

Where does Plexara run?

Plexara is a managed deployment operated by Deasil Works on infrastructure we run across six US data center facilities. AI agents reach Plexara over the standard MCP transport. There is no SaaS marketplace tier and nothing to install on your laptop.

Can Plexara federate across multiple data sources?

Yes. The Trino federation layer routes a single SQL query across PostgreSQL, Iceberg, Snowflake, S3, Kafka, Elastic, and 30+ other connectors. Agents write standard SQL without knowing where the data physically lives.

How does Plexara handle PII and sensitive data?

Persona-based access control restricts which tools and which data an agent can see, mapped to your existing identity provider. Default-deny applies to anything not explicitly allowed. Every tool call is logged with user identity, persona, and result so sensitive-data access is auditable end to end.

Is there an API outside of MCP?

Yes. Plexara exposes a REST API covering assets, collections, knowledge, memory, prompts, personas, audit, governance, and tool execution, so non-MCP systems can integrate the same governed surface. The MCP server and the REST API share one identity, audit, and persona model.

Product

The Governed Context Layer

Connect your AI agent to Plexara and it becomes an expert on your business. Plexara gives AI the ability to capture, apply, and utilize knowledge of your data. The more you use it, the smarter your AI gets and the better your results.

Six Pillars

What Plexara Does

Query Federation

Federated SQL across your entire data estate through Trino. A single query can join PostgreSQL, Elasticsearch, Iceberg, Cassandra, and 40+ other sources without moving data. Multi-connection routing lets agents reach separate Trino clusters through one MCP endpoint. Read-only enforcement and query limits keep production systems safe.

Learn more

Semantic Search and Enrichment

Every tool response is automatically enriched with business context from DataHub. When an agent describes a table, the response includes column descriptions, owners, tags, glossary terms, lineage, and quality scores. When an agent searches the catalog, results show which datasets are queryable and their resolved table paths. One call replaces four.

Learn more

Memory

Persistent memory across sessions using LOCOMO dimensions: knowledge, events, entities, relationships, and preferences. Multi-strategy recall surfaces relevant prior context automatically through entity lookup, semantic vector similarity, DataHub lineage graph traversal, or all three combined. The platform remembers what you taught it.

Learn more

Knowledge Capture

Every conversation is an opportunity to improve your data catalog. User corrections, agent-discovered insights, and enrichment gap flags are captured and flow through an admin review pipeline before being written back to DataHub as governed documentation. Nothing changes without human approval. Every changeset is tracked and reversible.

Learn more

Asset Management

AI-generated analyses become organizational assets. Interactive dashboards, reports, charts, and documents are saved with provenance tracking, versioned with full history, organized into curated collections, and shared across the team. Prompts codify repeatable workflows at platform, team, and personal scope.

Learn more

Personas and RBAC

Role-based access control that maps identity provider roles to tool and connection allow and deny patterns. Default-deny posture means no persona equals zero access. Tool and connection visibility filtering hides unauthorized tools and data sources from agents, reducing token consumption and preventing access attempts. Fail-closed security on every request.

Learn more

One Endpoint

Greater Than the Sum of Its Parts

Plexara does not just connect Trino, DataHub, and S3. It interweaves them. A query result carries catalog context. A catalog search reveals what is queryable. A storage object surfaces its lineage. Each service enriches the others at the protocol level, producing responses that no single system could generate alone.

This interweaving replaces the need to stitch together three to five separate tools: catalog, semantic layer, query engine, observability, and governance. The result is not just fewer moving parts. It is a single MCP endpoint where query execution, business context, and governance enforcement are inseparable.

Common questions

Plexara Product FAQ

: Any client that speaks the Model Context Protocol. That includes Claude Desktop, ChatGPT, the Anthropic and OpenAI SDKs, Cursor, Continue, and custom agents you build in-house. Plexara is the server; the client is your choice.
: Plexara is a managed deployment operated by Deasil Works on infrastructure we run across six US data center facilities. AI agents reach Plexara over the standard MCP transport. There is no SaaS marketplace tier and nothing to install on your laptop.
: Yes. The Trino federation layer routes a single SQL query across PostgreSQL, Iceberg, Snowflake, S3, Kafka, Elastic, and 30+ other connectors. Agents write standard SQL without knowing where the data physically lives.
: Persona-based access control restricts which tools and which data an agent can see, mapped to your existing identity provider. Default-deny applies to anything not explicitly allowed. Every tool call is logged with user identity, persona, and result so sensitive-data access is auditable end to end.
: Yes. Plexara exposes a REST API covering assets, collections, knowledge, memory, prompts, personas, audit, governance, and tool execution, so non-MCP systems can integrate the same governed surface. The MCP server and the REST API share one identity, audit, and persona model.

Deep Dive

Semantic Enrichment

How bidirectional enrichment gives every tool response complete business context.

Continue