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., "@JSON MCP Server query https://dummyjson.com/products and return average price by category"
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.
A JSON Model Context Protocol (MCP) server implementation for querying and manipulating JSON data. This server enables LLMs to interact with JSON data through a set of standardized tools.
# Using npx with specific version (recommended)
npx @gongrzhe/server-json-mcp@1.0.3
# Install specific version globally
npm install -g @gongrzhe/server-json-mcp@1.0.3
# Run after global installation
server-json-mcpRelated MCP server: Fetch JSONPath MCP
query
Query JSON data using JSONPath syntax with extended operations
Input:
url (string): URL of the JSON data source
jsonPath (string): JSONPath expression with optional operations
filter
Filter JSON data using conditions
Input:
url (string): URL of the JSON data source
jsonPath (string): Base JSONPath expression
condition (string): Filter condition
Slicing: $[0:5], $[-3:], $[1:4]
Sorting: $.sort(price), $.sort(-price)
Distinct: $.distinct()
Transformations:
Map: $.map(fieldName)
Flatten: $.flatten()
Union: $.union([1,2,3])
Intersection: $.intersection([1,2,3])
Case: $.toLowerCase(), $.toUpperCase()
Tests: $.startsWith('test'), $.endsWith('test')
Search: $.contains('test'), $.matches('pattern')
Math: $.math(+10), $.pow2()
Rounding: $.round(), $.floor(), $.ceil()
Functions: $.abs(), $.sqrt()
Format: $.format('YYYY-MM-DD')
Check: $.isToday()
Modify: $.add(1, 'days')
Group: $.groupBy(category)
Stats: $.sum(price), $.avg(price), $.min(price), $.max(price)
To use this server with the Claude Desktop app, add the following configuration to your claude_desktop_config.json:
{
"json": {
"command": "npx",
"args": [
"@gongrzhe/server-json-mcp@1.0.3"
]
}
}Alternatively, you can use the node command directly if you have the package installed:
{
"json": {
"command": "node",
"args": [
"path/to/build/index.js"
]
}
}Clone the repository
Install dependencies:
npm installBuild the project:
npm run buildAll JSONPath expressions start with $ representing the root object
Array indices are zero-based
String values in operations should be wrapped in quotes
Date operations support 'days', 'months', and 'years' units
Numeric operations support basic arithmetic operators (+, -, *, /)
MIT
Filter JSON data using conditions
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL of the JSON data source | |
| jsonPath | Yes | Base JSONPath expression | |
| condition | Yes | Filter condition (e.g. @.price < 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Filter' implies a read-only operation, the description doesn't clarify whether this tool fetches data from a URL, processes it locally, or has any side effects like caching. It also omits details about error handling, performance, or output format, leaving significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words, making it appropriately concise. However, it lacks front-loading of critical information—it doesn't immediately clarify the tool's scope or differentiate it from siblings, which slightly reduces its effectiveness despite the brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a tool that filters JSON data from a URL with three required parameters and no output schema, the description is incomplete. It fails to explain the output format, error conditions, or how the filtering integrates with the data source. Without annotations or an output schema, the agent lacks sufficient context to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning the input schema already documents all three parameters with descriptions. The tool description adds no additional meaning beyond what the schema provides, such as explaining how parameters interact or providing usage examples. However, since the schema is comprehensive, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Filter JSON data using conditions' states the tool's purpose with a clear verb ('Filter') and resource ('JSON data'), but it's vague about scope and doesn't distinguish from its sibling 'query'. It doesn't specify what kind of filtering or what the output looks like, leaving the agent uncertain about the exact operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its sibling 'query', nor does it mention any prerequisites or alternative scenarios. Without any context about when this tool is appropriate, the agent must guess based on the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query JSON data using JSONPath syntax
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL of the JSON data source | |
| jsonPath | Yes | JSONPath expression (e.g. $.store.book[*].author) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool queries JSON data but doesn't disclose behavioral traits like error handling, performance implications, rate limits, or what happens if the URL is invalid or JSONPath is malformed. For a tool with no annotations, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Query JSON data using JSONPath syntax.' It is front-loaded with the core purpose and has zero waste, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of querying external JSON data, the description is incomplete. No annotations exist, and there's no output schema, so the agent lacks information on return values, error cases, or behavioral constraints. The description doesn't compensate for these gaps, making it inadequate for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with clear descriptions for both parameters ('jsonPath' and 'url'). The description adds minimal value beyond the schema, as it only reiterates the use of JSONPath without providing additional syntax or format details. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Query JSON data using JSONPath syntax.' It specifies the verb ('query'), resource ('JSON data'), and method ('JSONPath syntax'). However, it doesn't explicitly differentiate from the sibling tool 'filter,' which might have overlapping functionality, preventing a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'filter' or any other context for usage, such as prerequisites or scenarios where this tool is preferred. This leaves the agent with minimal direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.3filterqueryScored across 2 tools
Both tools operate on JSON data to extract subsets, and 'filter' is essentially a restricted form of JSONPath querying, so an agent could reasonably pick either for a filtering need. The descriptions do differentiate them by mechanism (JSONPath syntax vs. conditions), which helps, but the boundary is fuzzy.
Both names are single lowercase verbs (query, filter) following the exact same convention. There is no mixing of styles or verb forms.
Two tools is thin for a server whose domain (JSON manipulation) typically involves parsing, validation, transformation, and mutation. It is defensible for a narrowly scoped read-only query server, but borderline.
The surface offers only read/extract operations; there is no parsing, validation, path construction, or any modification of JSON (set/merge/delete). Agents needing to inspect or transform JSON beyond querying and filtering will hit dead ends.
Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
Exactly 50 data transformation and live web verification tools for AI agents.
Turn any public webpage into JSON with AI, save it as a live JSON API, and call it from your agent.
500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
