MCP Server: Trend Data Persister
Flow-Research
README
MCP Server: Trend Data Persister
This project implements a Model Context Protocol (MCP) server using Python (fastmcp
) to persist trend data (upward or downward) into a PostgreSQL database.
The server exposes a single tool, persist-trend-data
, which accepts:
-
datasource_url
: The connection string for the target PostgreSQL database. -
json_data
: A JSON object representing the trend. It must match one of the following schemas:- Upward Trend:
{ "trend": "upward", "rockstars": [ { "name": "string", "department": "string", "amount": integer }, ... ] }
- Downward Trend:
{ "trend": "downward", "culprits": [ { "name": "string", "department": "string", "amount": integer }, ... ] }
- Upward Trend:
Functionality:
Based on the trend
value in json_data
:
- If
trend
is "upward", it ensures a table namedupward_trend_rockstars
exists (with columnsid
,name
,department
,amount
). It then inserts the data from therockstars
array into this table. - If
trend
is "downward", it ensures a table nameddownward_trend_culprits
exists (with the same columns). It then inserts the data from theculprits
array into this table. - The tool uses Pydantic for input validation and
psycopg2
to interact with the PostgreSQL database.
Prerequisites
- Python (>=3.10 recommended, as specified in pyproject.toml)
make
uv
(Optional, Makefile will fallback topython -m venv
andpip
ifuv
is not found)- Access to a running PostgreSQL database.
Setup and Running
A Makefile is provided for convenience.
- Clone/Navigate: Go into the project directory:
cd /path/to/mcp-server-trend-persister
- Run the Server:
The setup will install dependencies, run the mcp server and inspect it. Also the mcp server will listen for requests via standard input/output.make
Makefile Targets
The following targets are available in the Makefile
:
make install
: Creates/updates the.venv
virtual environment and installs dependencies usinguv
(preferred) orpip
.make run
: Runs the MCP server (persister.py
) using the Python interpreter from.venv
.make inspect
: Inspects the tools defined inpersister.py
using the MCP inspector (npx @modelcontextprotocol/inspector uv run persister.py
). Depends oninstall
.make lint
: Placeholder for running code linters (e.g., Ruff, Black).make clean
: Removes the virtual environment, cache files, and other build artifacts.make help
: Shows the list of available targets.
Integration with MCP Clients
Configure your MCP client (like the one mentioned in the context) to connect to this server. When using the Makefile, the command to launch the server simplifies.
Example configuration snippet:
{
"mcpServers": {
"trend-persister": {
"command": "make",
"args": [
"run" // Target to execute
],
"cwd": "/Users/julian/Documents/Code/Learning/MCP/mcp-server-trend-persister" // Important: Set the working directory
},
// ... other servers
}
}
Ensure the cwd
path points to the correct project directory where the Makefile
resides.
Example Tool Request
An MCP client would send a request like:
{
"toolName": "persist-trend-data",
"arguments": {
"datasource_url": "postgresql://your_user:your_password@your_host:5432/your_db",
"json_data": {
"trend": "upward",
"rockstars": [
{ "name": "Alice", "department": "Sales", "amount": 50000 },
{ "name": "Bob", "department": "Engineering", "amount": 60000 }
]
}
}
}
Recommended Servers
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Mathematica Documentation MCP server
A server that provides access to Mathematica documentation through FastMCP, enabling users to retrieve function documentation and list package symbols from Wolfram Mathematica.
kb-mcp-server
An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded
Research MCP Server
The server functions as an MCP server to interact with Notion for retrieving and creating survey data, integrating with the Claude Desktop Client for conducting and reviewing surveys.