What makes this different from running JavaScript?

This MCP uses a simplified JMESPath syntax. It is deterministic and avoids the security and unpredictability risks of executing arbitrary JavaScript.

Which AI clients can use this MCP?

You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I check my query before running it?

Yes, you can use the validate_query_syntax capability to ensure your query is formatted correctly.

How do I know what keys are in my JSON file?

You can use the inspect_json_schema capability to see the top-level structure of your dataset.

Do I need to host this myself?

No, Vinkius hosts and manages the MCP for you. You just connect it to your client.

What tokens are supported in the query string?

The engine supports three primary tokens: '.' for property access, '[]' for array flattening, and '*' for wildcards.

How can I verify if my query is valid before running it?

You can use the validate_query_syntax capability to check your string for structural validity.

Does this capability modify my original JSON data?

No, the engine treats the input JSON as a read-only structure and builds a new resulting structure without modifying the source.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Jmespath Query Executor to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull exact data points from deep JSON structures without writing risky code.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Jmespath Query Executor.

01
Execute jmespath query
This capability runs a JMESPath-style query against your JSON data to return specific subsets or values.
02
Validate query syntax
Use this to check if your JMESPath query string is formatted correctly before you try to run it.
03
Inspect JSON schema
This capability looks at the top-level structure of your JSON so you know what keys are available to query.

Real work

What teams actually run

API Response Parsing

Your agent queries a large API response to find a specific user ID or token.

Log Analysis

You use the capability to pull specific error codes from a massive JSON log file.

Configuration Auditing

The AI checks specific nested settings within a JSON configuration file.

Data Transformation

You extract specific subsets of data to prepare them for further processing.

One connector, every AI

Jmespath Query Executor works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Jmespath Query Executor to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

698ms average. Fast in production.

Jmespath Query Executor is checked daily against the live service.

Daily averagePeak 845ms

Oct 3Today

Fastest day: 564ms
Slowest day: 845ms
14-day trend: Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Jmespath Query Executor, so you can see the experience inside your AI.

It does not authenticate your account with Jmespath Query Executor. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Jmespath Query Executor Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_6aXPbraQWAHtprq4O0Qtanxssza6E78IBBMaRWJX/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Jmespath Query Executor capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "jmespath-query-executor-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_6aXPbraQWAHtprq4O0Qtanxssza6E78IBBMaRWJX/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Jmespath Query Executor in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Jmespath Query Executor owners hand off.

This MCP is built for technical users who need to feed structured data into their AI workflows.

01
Backend Developers
They hand off complex API responses to the AI to extract specific fields for testing.
02
Data Engineers
They use it to parse through large JSON files to find specific nested attributes.
03
DevOps Engineers
They query configuration files or log outputs to pull out relevant status indicators.

FAQ

Questions Jmespath Query Executor owners ask.

01
What makes this different from running JavaScript?
This MCP uses a simplified JMESPath syntax. It is deterministic and avoids the security and unpredictability risks of executing arbitrary JavaScript.
02
Which AI clients can use this MCP?
You can use this with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
03
Can I check my query before running it?
Yes, you can use the validate_query_syntax capability to ensure your query is formatted correctly.
04
How do I know what keys are in my JSON file?
You can use the inspect_json_schema capability to see the top-level structure of your dataset.
05
Do I need to host this myself?
No, Vinkius hosts and manages the MCP for you. You just connect it to your client.
06
What tokens are supported in the query string?
The engine supports three primary tokens: '.' for property access, '[]' for array flattening, and '*' for wildcards.
07
How can I verify if my query is valid before running it?
You can use the validate_query_syntax capability to check your string for structural validity.
08
Does this capability modify my original JSON data?
No, the engine treats the input JSON as a read-only structure and builds a new resulting structure without modifying the source.

Explore

More in Developer Tools

Connect Jmespath Query Executor to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Execute jmespath query

Validate query syntax

Inspect JSON schema

What teams actually run

API Response Parsing

Log Analysis

Configuration Auditing

Data Transformation

Building your own app? The connector is yours to use.

Jmespath Query Executor Connector

Claude Desktop

Backend Developers

Data Engineers

DevOps Engineers

What makes this different from running JavaScript?

Which AI clients can use this MCP?

Can I check my query before running it?

How do I know what keys are in my JSON file?

Do I need to host this myself?

What tokens are supported in the query string?

How can I verify if my query is valid before running it?

Does this capability modify my original JSON data?

JSON5 Resilient Parser AI Connector

JSON Path Query Engine AI Connector

JSONL Strict Parser AI Connector

JSONL Strict Parser AI Connector

Suggestions

JSONPath Query Executor AI Connector

URL Query String Deep Parser AI Connector

JSON-LD SEO Compiler AI Connector

Deterministic JSON Schema Gatekeeper AI Connector