Agentdata
AgentData — on-prem connectors + quickstart for the AgentData Data Fabric / Semantic Layer (REST + MCP)
Install
$ agentstack add mcp-biskilled-agentdata ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/mcp-biskilled-agentdata) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AgentData
AgentData is a Data Fabric / Semantic Layer that auto-discovers business entities across heterogeneous databases, maintains a unified semantic model, and serves analytical queries through a REST API and MCP — so people and LLMs can ask questions of your data in plain language.
This is the public repository for AgentData: the on-prem connectors you install to connect private databases, the connector protocol, and getting-started docs. The product itself (backend, UI, semantic engine) is hosted — you don't run it from here.
What's here
| Path | What it is | |------|------------| | [connectors/](connectors/) | On-prem connectors you install on your own network | | [connectors/relational/](connectors/relational/) | The relational connector — PostgreSQL, MySQL, SQL Server, SQLite (read sources and/or write staging DBs) | | [connectors/PROTOCOL.md](connectors/PROTOCOL.md) | The job contract between a connector and the backend (build your own in any language) | | [QUICKSTART.md](QUICKSTART.md) | Connect a database and run your first flow |
Why a connector?
A connector lets the hosted AgentData backend reach a database on your network without exposing it to the internet and without copying its data out. It runs inside your network, holds the database credentials locally, makes only outbound HTTPS calls (it polls — no inbound port), and returns only metadata and query/flow results. Raw rows and credentials never leave your machine.
AgentData (hosted) ◄── outbound HTTPS poll ── connector (your network) ──► your database
│ │
└──────────── metadata / results only ─────────┘Get started
See [QUICKSTART.md](QUICKSTART.md), then the connector you need — e.g. [connectors/relational/](connectors/relational/) for SQL databases.
License
[MIT](LICENSE) — you're free to read, run, and adapt the connectors for connecting your own systems to AgentData.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: biskilled
- Source: biskilled/agentdata
- License: MIT
- Homepage: https://agentdata.ui.biskilled.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.