JSONShelf

Deterministic JSON repair, validate, example-gen, schema-coerce for agents. Zero LLM, sub-10ms.

Should I use this

Quality & Safety

B
Description quality
85%
Schema completeness
78%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • LOWTool 'jsonshelf_repair' description lacks action verbin jsonshelf_repair
  • LOWTool 'jsonshelf_coerce' description lacks action verbin jsonshelf_coerce

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~262Tokens (tool definitions)
~424 BTypical response size
Minimal attention impact (0.20% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "jsonshelf": {
      "url": "https://jsonshelf.vercel.app/mcp"
    }
  }
}

Remote endpoints

https://jsonshelf.vercel.app/mcpstreamable-http

What it can do

Tool inventory

Tools (4)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪jsonshelf_repair(input, schema, mode)

Repair malformed JSON. Returns valid JSON plus a diff of what was fixed.

Input Schema

{
  "type": "object",
  "properties": {
    "input": {
      "type": "string",
      "description": "Malformed JSON as a string."
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON Schema to conform the output to."
    },
    "mode": {
      "type": "string",
      "enum": [
        "strict",
        "coerce"
      ],
      "default": "strict"
    }
  },
  "required": [
    "input"
  ]
}
⚪jsonshelf_validate(input, schema)

Validate JSON against a schema. Returns structured errors with JSON Pointer paths and remedies.

Input Schema

{
  "type": "object",
  "properties": {
    "input": {},
    "schema": {
      "type": "object"
    }
  },
  "required": [
    "input",
    "schema"
  ]
}
⚪jsonshelf_example(schema)

Generate a minimal valid example matching a JSON schema.

Input Schema

{
  "type": "object",
  "properties": {
    "schema": {
      "type": "object"
    }
  },
  "required": [
    "schema"
  ]
}
⚪jsonshelf_coerce(input, schema)

Soft-cast values to match a schema (string "42" → 42 for integer fields, etc.).

Input Schema

{
  "type": "object",
  "properties": {
    "input": {},
    "schema": {
      "type": "object"
    }
  },
  "required": [
    "input",
    "schema"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded4 tools
verifiedversion not recorded4 tools
verifiedversion not recorded4 tools