About af-databridge
af-databridge is a dependency-free MCP server for converting CSV text to JSON and calculating weighted KPI scores. It suits workflows that need lightweight data conversion and normalized KPI evaluation.
Key features
- 01CSV-to-JSON conversion
- 02Delimiter detection and quoted-field handling
- 03Number and boolean type inference
- 04Weighted KPI scoring with direction normalization
Use cases
- 01Convert delimited CSV text for downstream processing
- 02Score KPIs with higher- or lower-is-better targets
MCP support
It exposes `csv_to_json` and `kpi_score` as tools to MCP clients over JSON-RPC 2.0 on stdio.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAF DataBridge MCP
A zero-dependency Model Context Protocol server with two tools:
| Tool | What it does |
|---|---|
csv_to_json | Converts CSV text to JSON. Sniffs the delimiter (, ; tab ` |
kpi_score | Scores weighted KPIs 0..1 with higher-is-better or lower-is-better normalisation. |
No dependencies. No network calls. Runs on Node 18+.
Install and run
node server.mjs # speaks JSON-RPC 2.0 over stdio
Client config (e.g. Claude Desktop, Cursor, Cline):
{ "mcpServers": { "af-databridge": { "command": "node", "args": ["/path/to/af-databridge-mcp/server.mjs"] } } }
Example
Input CSV (semicolon-delimited, quoted comma, mixed types):
sku;name;price;in_stock
A1;"Widget, small";4.50;true
B2;Gadget;12;false
csv_to_json returns:
[
{ "sku": "A1", "name": "Widget, small", "price": 4.5, "in_stock": true },
{ "sku": "B2", "name": "Gadget", "price": 12, "in_stock": false }
]
Tests
node test.mjs # 9 passed
Verified: sniffDelimiter picks ; and , correctly, quoted commas survive, blank rows are skipped, type inference maps 12 to 12, 4.50 to 4.5, true to true, and KPI weighting is exact (0.75 for 3:1 weights at 100%/0%).
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.