json-mcp-server
JSON MCP
Der Model Context Protocol (MCP) -Server ermöglicht LLMs die effiziente Interaktion mit JSON-Dateien. Mit JSON MCP können Sie bestimmte Daten teilen , zusammenführen und suchen sowie JSON-Dateien anhand definierter Bedingungen validieren .
🌟 Hauptfunktionen
✅ Schnell und leicht
✅ LLM-freundliche Funktionalität
Related MCP server: mcp-server-test
🎥 Demo
Unten sehen Sie eine Demo, die die split -Funktionalität vorführt:

🔧 Anwendungsfälle (Tools)
1. split
Teilen Sie eine JSON-Datei in eine angegebene Anzahl von Objekten auf.
Hinweis: Der Dateipfad muss angegeben werden.
Beispiel für eine Eingabeaufforderung:
Split JSON file from /Users/json-mcp/tests/merged.json
5 objects per file2. merge
JSON-Dateien zu einer einzigen JSON-Datei zusammenführen
Hinweis: Der Ordnerpfad sollte angegeben werden
Beispiel für eine Eingabeaufforderung:
Merge json files from /Users/json-mcp/tests⚙️ Konfiguration
Manuelle VS Code-Konfiguration
Um den JSON-MCP-Server manuell in VS Code zu konfigurieren, aktualisieren Sie die Datei „Benutzereinstellungen“ (JSON) :
{
"mcp": {
"servers": {
"json-mcp-server": {
"command": "npx",
"args": ["json-mcp-server@latest"]
}
}
}
}Installation in VS Code
Sie können den JSON MCP-Server mithilfe der VS Code CLI installieren:
# For VS Code
code --add-mcp '{"name":"json-mcp-server","command":"npx","args": ["json-mcp-server@latest"]}'Nach der Installation steht der JSON-MCP-Server zur Verwendung mit Ihrem GitHub Copilot-Agent in VS Code zur Verfügung.
Claude Desktop
So installieren Sie json-mcp für Claude Desktop automatisch über Smithery :
npx -y @smithery/cli install @VadimNastoyashchy/json-mcp --client claude⚙️ Installationsserver
Global installieren
npm install -g json-mcp-server@latestNach globaler Installation ausführen
json-mcp-serverVerwenden von npx mit der neuesten Version (empfohlen)
npx json-mcp-server@latestAvailable Tools
2 toolsmergeC
Merge JSON files into a one JSON file
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only says 'merge', without disclosing critical behaviors like conflict resolution, merge strategy (shallow vs deep), output location, or whether it modifies input files.
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 short sentence, which is concise but sacrifices clarity. It is front-loaded but lacks necessary detail.
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 one parameter, no output schema, and no annotations, the description is too incomplete. It does not explain merge behavior, input constraints, or output format, leaving significant gaps for an agent.
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?
The input schema has 0% description coverage for the 'path' parameter, and the description does not explain what 'path' represents. It could be a file path or directory; the ambiguity reduces usefulness.
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 merges JSON files into one, with a verb 'merge' and resource 'JSON files'. It distinguishes from the sibling 'split' by being the opposite operation. However, it lacks specificity about what 'path' refers to (a single file? a directory?)
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?
No guidance on when to use this tool versus alternatives. The sibling 'split' suggests a complementary tool, but no explicit when-to-use or when-not-to-use is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
splitB
Split a JSON file into a specified number of objects
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| numObjects | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose side effects (e.g., whether the original file is modified or a new file created), required permissions, or other behavioral traits. With no annotations, the description carries the full burden but provides minimal info.
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?
Single sentence, no unnecessary words. However, the description could benefit from additional structure to cover key behavioral aspects.
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?
For a simple tool with two parameters, the description is minimally adequate but leaves questions unanswered, such as output behavior and impact on input file. Missing details reduce completeness.
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 coverage is 0%, and the description adds no meaning beyond the schema. For example, 'path' and 'numObjects' are not detailed—no clarification on file format, location constraints, or how numObjects is applied.
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 action (split) and the resource (JSON file). It distinguishes from the sibling tool 'merge' by implying opposite functionality.
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?
No guidance on when to use this tool versus alternatives (e.g., 'merge'). No context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
merge - First observed
split
TDQS
Scored across 2 tools
Merge and split are clearly opposite operations. An agent can easily distinguish their purposes without ambiguity.
Both tools use concise, single-word verbs (merge, split) following a consistent pattern.
Two tools is slightly below the typical well-scoped range, but the server's narrow focus on merge/split operations justifies this minimal set.
The server covers the core merge and split operations for JSON files. Minor gaps like transform or validate exist, but the surface is complete for its stated purpose.
Maintenance
Related MCP Connectors
The official MCP Server for the Mux API
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Related MCP Servers
- MIT
- -
- AlicenseNot gradedqualityBmaintenanceJson AI - MCP server providing AI-powered tools and automation by MEOK AI Labs13 npm39 PyPIMIT
- AlicenseNot gradedqualityAmaintenanceMCP server for reading, querying, and filtering local JSON files with extended JSONPath syntax, supporting sorting, aggregations, and complex conditions.369 npm2MIT