MCP Examples

This page demonstrates common workflows using the jpx MCP server with Claude or other AI assistants.

Data Exploration

Understanding Unknown JSON

When you receive unfamiliar JSON data, start by exploring its structure:

User: I have this API response, can you help me understand it?

Claude: Let me analyze the structure first.

[Uses stats tool]
{
  "input": "{\"users\": [{\"id\": 1, \"profile\": {\"name\": \"Alice\", \"settings\": {\"theme\": \"dark\"}}}]}"
}

Result: Object with 1 key, depth 4, contains array of 1 object

[Uses paths tool]
{
  "input": "{\"users\": [{\"id\": 1, \"profile\": {\"name\": \"Alice\"}}]}",
  "include_types": true
}

Result:
  users: array
  users.0: object
  users.0.id: number
  users.0.profile: object
  users.0.profile.name: string

Finding the Right Function

When you need to transform data but aren't sure which function to use:

User: I need to remove duplicate entries from an array

Claude: Let me search for relevant functions.

[Uses search tool]
{
  "query": "remove duplicates array unique"
}

Result: Found unique(), distinct(), dedupe() - all do similar things.

[Uses describe tool]
{
  "name": "unique"
}

Result: unique(array) - Returns array with duplicate elements removed, preserving order.

Query Building

Iterative Query Development

Build complex queries step by step:

User: Help me extract active premium users with their subscription dates

Claude: Let me build this query incrementally.

[Uses evaluate tool - Step 1: Filter active users]
{
  "expression": "users[?status == `active`]",
  "input": "{\"users\": [{\"name\": \"Alice\", \"status\": \"active\", \"plan\": \"premium\", \"since\": \"2024-01-15\"}, {\"name\": \"Bob\", \"status\": \"inactive\", \"plan\": \"free\", \"since\": \"2023-06-01\"}]}"
}

[Uses evaluate tool - Step 2: Add premium filter]
{
  "expression": "users[?status == `active` && plan == `premium`]",
  "input": "..."
}

[Uses evaluate tool - Step 3: Project fields]
{
  "expression": "users[?status == `active` && plan == `premium`].{name: name, member_since: since}",
  "input": "..."
}

Final query: users[?status == `active` && plan == `premium`].{name: name, member_since: since}

Validating Expressions

Check syntax before running on large datasets:

[Uses validate tool]
{
  "expression": "users[?active].name | sort(@"
}

Result: Invalid - unclosed parenthesis at position 27

[Uses validate tool]
{
  "expression": "users[?active].name | sort(@)"
}

Result: Valid expression

Batch Operations

Multiple Extractions

Extract several pieces of information at once:

[Uses batch_evaluate tool]
{
  "input": "{\"items\": [1, 2, 3, 4, 5], \"metadata\": {\"count\": 5, \"type\": \"numbers\"}}",
  "expressions": [
    "length(items)",
    "sum(items)",
    "avg(items)",
    "metadata.type"
  ]
}

Result:
  length(items): 5
  sum(items): 15
  avg(items): 3
  metadata.type: "numbers"

File Operations

Working with Large Files

Query files directly without loading into memory:

[Uses evaluate_file tool]
{
  "file_path": "/path/to/large-dataset.json",
  "expression": "records[?timestamp > `2024-01-01`] | length(@)"
}

Result: 15234 records match the filter

JSON Transformations

Generating Patches

Track changes between document versions:

[Uses diff tool]
{
  "source": "{\"version\": 1, \"config\": {\"debug\": true, \"timeout\": 30}}",
  "target": "{\"version\": 2, \"config\": {\"debug\": false, \"timeout\": 60, \"retries\": 3}}"
}

Result:
[
  {"op": "replace", "path": "/version", "value": 2},
  {"op": "replace", "path": "/config/debug", "value": false},
  {"op": "replace", "path": "/config/timeout", "value": 60},
  {"op": "add", "path": "/config/retries", "value": 3}
]

Applying Updates

Merge configuration updates:

[Uses merge tool]
{
  "input": "{\"database\": {\"host\": \"localhost\", \"port\": 5432}, \"cache\": {\"enabled\": true}}",
  "patch": "{\"database\": {\"host\": \"db.example.com\"}, \"cache\": null}"
}

Result:
{
  "database": {"host": "db.example.com", "port": 5432}
}

Note: Setting a key to null in merge patch removes it.

Function Discovery Workflows

Learning New Functions

Explore related functionality:

[Uses similar tool]
{
  "function": "snake_case"
}

Result:
  Same category: camel_case, kebab_case, pascal_case, title_case
  Similar signature: upper, lower, capitalize
  Related concepts: snake_keys, camel_keys (for object keys)

Category Exploration

See all functions in a category:

[Uses functions tool]
{
  "category": "datetime"
}

Result:
  now() - Current timestamp
  format_date(date, format) - Format date string
  parse_date(string, format) - Parse date from string
  date_add(date, amount, unit) - Add time to date
  date_diff(date1, date2, unit) - Difference between dates
  ...

Multi-Server Discovery

When working with multiple MCP servers, use discovery tools to find the right tool across all servers:

[Uses query_tools tool]
{
  "query": "send email notification",
  "top_k": 5
}

Result:
  1. notifications:send_email (score: 12.4)
  2. mailer:compose_message (score: 8.2)
  3. alerts:notify_user (score: 6.1)

See Multi-Server Discovery for more details on setting up cross-server tool search.