Universal JSON Agent MCP
Click on "Install 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., "@Universal JSON Agent MCPLoad the file sales.json and calculate total revenue"
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.
Universal JSON Agent MCP
Talk to your JSON files using natural language.
26 powerful tools to load, explore, query, aggregate, transform, and export — right from your AI editor.
uv tool install universal-json-agent-mcpGetting Started · 26 Tools · Web Server · Development
Why?
Working with JSON shouldn't require writing a script every time. This tool lets you ask questions in plain English and get answers instantly.
You: What's the total budget across all missions?
AI: The total budget across all missions is $18,250,000,000.50
(Used tools: load_json → sum_values)Supported Clients
Any MCP Client | |||
VS Code / Copilot | Claude Desktop | Cursor | stdio |
⚡ Getting Started
1. Install
uv tool install universal-json-agent-mcp # install CLI once
uvx universal-json-agent-mcp # run without installing
uv add universal-json-agent-mcp # add dependency to your project2. Configure your editor
Create .vscode/mcp.json in your workspace:
{
"servers": {
"universal-json-agent": {
"type": "stdio",
"command": "universal-json-agent-mcp"
}
}
}Tip: Prefer zero-install? Use
"command": "uvx"with"args": ["universal-json-agent-mcp"]instead.
Add to claude_desktop_config.json:
{
"mcpServers": {
"universal-json-agent": {
"command": "universal-json-agent-mcp"
}
}
}Add to your Cursor MCP settings:
{
"mcpServers": {
"universal-json-agent": {
"command": "universal-json-agent-mcp"
}
}
}universal-json-agent-mcp
# or
uv run python -m universal_json_agent_mcpStarts on stdio — pipe any MCP client into it.
3. Start asking questions
> Load data/orders.json and tell me what's inside
> How many missions have status "in_progress"?
> What's the total budget across all missions?
> Filter personnel where role contains "engineer"
> Sort by priority descending and show codenames
> Export the filtered results to CSV🛠 Tools Reference
Load & Manage
Tool | What it does |
| Load a JSON file from disk into memory |
| List all loaded documents with metadata |
| Remove a document from memory |
Explore
Tool | What it does |
| Get keys of an object or index range of an array |
| Retrieve value at a path (auto-truncated at 10 KB) |
| Return the JSON type at a path |
| Schema-like skeleton — keys, types, nesting |
Query
Tool | What it does |
| Run JSONPath — |
| Filter by condition: |
| Full-text search across all string values |
Aggregate
Tool | What it does |
| Count items in an array or keys in an object |
| Sum numeric values at a JSONPath |
| Get min and max of numeric values |
| Distinct values at a JSONPath |
| Frequency table — like pandas |
Transform
Tool | What it does |
| Flatten nested objects to dot-notation pairs |
| Project specific fields from array objects |
| Group objects by a field value |
| Sort objects by a field |
| Random N items from an array |
Analytics
Tool | What it does |
| Stats: count, mean, std, min, max, percentiles |
| Compound filters with AND / OR logic |
| Diff two values — added, removed, changed keys |
Export
Tool | What it does |
| Export array of objects to CSV file |
| Export a value to a new JSON file |
Introspect
Tool | What it does |
| List every unique leaf path with types |
🌐 Web Server Subproject (web/)
Optional FastAPI + LangChain web-server subproject inside this repo, wrapping all 26 root MCP tools for integrations, dashboards, or non-MCP workflows.
uv sync --extra web # install web deps with uv
cp .env.example .env # add your OpenRouter key
uv run python -m web.run --port 8000 # start server with uv
# open docs in browser: http://127.0.0.1:8000/docsEndpoints
Method | Endpoint | Description |
|
| Health check |
|
| Upload JSON + ask a question |
|
| Reference a file on disk + ask a question |
|
| Interactive Swagger UI |
Example
curl -X POST http://localhost:8000/query \
-F "file=@data/missions.json" \
-F "query=What's the total budget?"{
"answer": "The total budget across all missions is $18,250,000,000.50",
"tools_used": ["load_json", "sum_values"]
}Configuration
Variable | Required | Default | Description |
| ✅ | — | Your OpenRouter API key |
| — |
| Any supported model |
🧑💻 Development
git clone https://github.com/GautamVhavle/universal-json-agent.git
cd universal-json-agent
uv sync --extra dev
uv run pytest # 489 testsuv run pytest -v # verbose
uv run pytest tests/test_tools/test_aggregate.py # one file
uv run pytest -k "test_filter" # by patternReleasing
Releases are fully automated via GitHub Actions:
git tag v0.3.0 -m "v0.3.0"
git push origin v0.3.0Then create a GitHub Release for the tag — CI runs tests, builds, and publishes to PyPI.
Troubleshooting
Verify the config file exists (
.vscode/mcp.jsonfor VS Code)Check the command is on your PATH:
which universal-json-agent-mcpRestart the editor
You need to load a file first. Ask your AI: "Load the file data/example.json" — this calls load_json behind the scenes.
Large results are capped at ~10 KB. Use more specific paths, filters, or pick_fields to narrow results.
The model provider is rate-limiting you. Wait a moment or switch to a different model in your .env file.
uv sync --extra webMIT License · Built with ❤️ by Gautam Vhavle · Star this repo if it helped you ⭐
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/GautamVhavle/universal-json-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server