mcp-server-example
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-example Which readers support BLE and how do I subscribe to events?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-server-example
A minimal Model Context Protocol server in TypeScript. It exposes a small device catalog and SDK method reference to AI agents through three read-scoped tools, so an integrator can ask an agent questions like "which readers support BLE?" or "how do I subscribe to access events?" instead of reading documentation.
This is a sanitized, self-contained echo of a pattern I've used in production: put an MCP server in front of an SDK so third-party integrators can build against it through an agent.
The design point
The tool schemas are the governance layer. There is deliberately no unlock_door tool in this server. An agent connected to it can list devices, get device details, and search SDK methods, and nothing else. "What can the AI do?" becomes a precise, auditable question answered by the schema, not by trusting the model to behave.
Related MCP server: wissens-enablement-agent
Tools
Tool | Scope |
| Read. Optional filters by category and capability |
| Read. Single device by id |
| Read. Keyword search over SDK method reference |
Run it
npm install
npm run inspect # opens the MCP Inspector against this serverOr wire it into Claude Desktop / Cursor as a stdio server:
{
"mcpServers": {
"example": { "command": "npx", "args": ["tsx", "/path/to/mcp-server-example/src/index.ts"] }
}
}Then ask: "Which readers support BLE and what SDK call subscribes to events?" and watch the agent chain list_devices and search_sdk.
What I'd add for a real deployment
An HTTP transport (SSE or streamable HTTP) for remote clients, with auth on the transport
Per-client scoping: which tools a given integrator's token can see
Audit logging of every tool invocation (who, what, when, arguments)
Write-scoped tools only behind explicit approval workflows
Available Tools
3 toolsget_deviceA
Get full details for a single device by id.
Inputs: id (required).
list_devicesA
List catalog devices. Optional filters: category (reader|controller|camera) and capability (e.g. 'ble', 'osdp').
Inputs: category, capability.
search_sdkA
Search SDK methods by keyword across name and description. Returns name, description, and the SDK version it appeared in.
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct operation: listing devices, retrieving a device detail, and searching SDK methods. No two tools overlap in purpose or output, so an agent can easily select the right one.
All tool names follow a clear lower_snake_case verb_noun pattern: list_devices, get_device, search_sdk. The convention is perfectly consistent across the set.
Three tools is on the smaller side, but the server appears focused on read-only device catalog and SDK lookup. The count is reasonable for a narrow purpose, though it might feel slightly thin if the server expected broader functionality.
For the implied read-only catalog use case, the coverage is adequate: list and get cover device data, and search covers SDK exploration. Missing create/update/delete operations are acceptable if the server is intentionally read-only, but a get_sdk_method or list_sdk_methods would round out the SDK side.
Maintenance
Related MCP Connectors
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
Read-only search of 2,189 AI agent tools (MCP servers, x402 APIs) with daily automated trust scores.
Read-only discovery of ChatGXT's integration catalog and public MCP capabilities.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search, read, and traverse documentation bundles in Open Knowledge Format via MCP tools.771 npm74MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to securely search and list internal company documents via MCP tools, so they can answer employee questions based on current internal documentation.-
- FlicenseAqualityCmaintenanceEnables AI agents to discover and query enterprise knowledge documents and business metrics through standardized MCP tools, supporting retrieval, structured sales/order analysis, anomaly scanning, and data lineage lookups.12-
- AlicenseNot gradedqualityBmaintenanceEnables privacy-preserving document retrieval by exposing read-only search tools over MCP, allowing agents to query local vector and structured indexes without sending data to the cloud.2MIT