Solution · AI data supply

Give AI systems current enterprise data

Keep retrieval stores in sync with operational systems, and expose Core Hub MCP tools for pipelines, reporting, and SQL under caller RBAC.

Explore AI data supply Talk to our team
OPERATIONAL SOURCES CAPTURED CONTINUOUSLY PostgreSQL · orders MongoDB · catalog Db2 for i · ledger log, journal, and change-stream capture continuous CDC Gluesync Core Hub one control plane row filters field functions defined functions only the rows and fields you allow leave the source RETRIEVAL STORES MongoDB · Couchbase Parquet in object storage kept current by CDC MCP CLIENT RBAC /mcp · /mcp/http pipelines · SQL tools caller's own role
  1. 01 Synchronize the retrieval store
  2. 02 Send only what belongs
  3. 03 Connect agents through MCP

The challenge

Models answer from whatever you last exported

Retrieval quality depends on how recent the underlying store is, and most AI data supply is still a scheduled dump out of the systems that hold the record.

01 / Staleness

Exports date immediately

A nightly extract into a retrieval store means answers reflect yesterday's inventory, pricing, or case status.

02 / Fragmentation

Context lives in several engines

The records a model needs are spread across relational, NoSQL, and file-based systems with different access paths.

03 / Governance

Agent access outruns permissions

Wiring an assistant straight into production databases spreads credentials and sidesteps the roles already defined.

How it works

Synchronize the stores, then expose them safely

Gluesync keeps AI-facing stores current with change data capture, shapes records on the way through, and lets MCP clients reach Core Hub without new privileges.

  1. 01

    Feed

    Synchronize the retrieval store

    Continuous CDC keeps document databases, object storage, and analytical targets aligned with the operational source.

  2. 02

    Shape

    Send only what belongs

    Row filters, field functions, and user-defined functions decide which records and fields ever leave the source.

  3. 03

    Expose

    Connect agents through MCP

    Connect to https://corehub-host.example/mcp/http with Authorization: Bearer YOUR_TOKEN, using a session JWT or a gsp_ personal API token. The embedded server exposes 112 built-in tools in Gluesync 2.3 (Beta) over SSE at /mcp and streamable HTTP at /mcp/http, plus optional per-session Query Studio database tools when enabled.

Gluesync capabilities

A supply line for retrieval and agent workflows

Gluesync keeps the data current and queryable for the layer that builds your embeddings and prompts, rather than generating them itself.

01

Core Hub MCP server

Available in Core Hub from 2.2.10.x, the embedded Model Context Protocol server applies the caller's bearer token and Control Plane RBAC. Gluesync 2.3 (Beta) expands the catalog to 112 tools, including Chronos, Core Hub webhooks, and email notifications.

  • 112 built-in tools in Gluesync 2.3 (Beta) for pipelines, agents, entities, sync, notifications, metrics, Chronos, Core Hub webhooks, email, mapping, Query Studio, groups and configuration, license, version, export, and Connections
  • Optional per-session Query Studio database tools when enabled
  • SSE /mcp and streamable HTTP /mcp/http transports
  • Read-only mode and tool allow-list controls

Core Hub MCP server

02

Continuously synchronized stores

Land current records where your retrieval layer already reads them, from document databases to object storage.

  • MongoDB and Couchbase targets
  • Parquet in S3, ADLS Gen2, and Cloud Storage
  • Composed document keys

MongoDB agent Custom document keys

03

Payload shaping and filtering

Decide at the pipeline level which rows and fields reach an AI-facing store, at both snapshot and CDC time.

  • Inclusive row-level filters
  • Field functions on values
  • User-defined functions

Data filtering User-defined functions

FAQ

Frequently asked questions

Answers about current AI data, retrieval stores, payload controls, and Core Hub MCP.

Does Gluesync generate embeddings or run a RAG model?

No. Gluesync keeps the databases and object stores behind retrieval workflows current and governed; the retrieval, embedding, and model layers remain yours.

How does Gluesync keep AI context fresh?

An initial snapshot seeds the AI-facing store, then CDC continuously delivers committed source changes instead of waiting for the next scheduled export.

Can data be filtered before it reaches an AI-facing store?

Yes. Row filters, field functions, and user-defined functions can control which records and values leave the source during snapshots and CDC.

How is Core Hub exposed to AI agents?

Core Hub includes an MCP server with SSE and streamable HTTP transports. Tool access uses the caller's bearer token, RBAC permissions, and configured tool controls.

Point your models at data that keeps moving

Start a trial or talk with MOLO17 about the stores, filters, and access model behind your AI workloads.

Request a free trial Talk to our team