jsonpath-plus Connector for AI agents.
1 live capability
Extract specific data from complex API responses without wasting tokens.
Waiting for input…
Why people use jsonpath-plus
JSON Path Query Engine for Precise API Data Extraction
This Connector changes that by letting your agent act as a filter. You provide the raw data and a simple path, and it hands your agent the exact values it needs. You get clean, usable data and a much lower token bill.
What Vinkius changes
You get the exact data you need without wasting tokens on the rest of the payload.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Parsing a massive e-commerce order list
A user wants to find the total price of all shipped items in a 2,000 item JSON.
- Real-world use case 02
Cleaning up a messy social media API
An app developer needs to pull only the author name and post ID from a huge nested response.
- Real-world use case 03
Extracting user IDs from a batch log
A dev needs to find every user ID that triggered an error in a massive JSON log file.
Complete set · 1capability
The complete jsonpath-plus capability set.
These are the exact actions your AI can choose when you ask it to work with jsonpath-plus.
01
1 capability in this set.
Part of 1 available through jsonpath-plus.
- 01 Capability
Query json
Pass a raw JSON string and a JSONPath expression to get all matching values. This lets your agent ignore the noise of a massive payload.
Set up in minutes
One URL. Then ask jsonpath-plus to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use jsonpath-plus from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it jsonpath-plus, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable jsonpath-plus for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the jsonpath-plus URL.
- Step 03
Save and start
Save the connection and enable jsonpath-plus in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"json-path-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using jsonpath-plus
Open Agent mode in chat and ask: "Using jsonpath-plus, help me...". 1 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"json-path-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using jsonpath-plus
Ask Copilot: "Using jsonpath-plus, help me...". 1 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"json-path-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using jsonpath-plus
Open Cascade and ask: "Using jsonpath-plus, help me...". 1 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"json-path-query-engine": {
"url": "https://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using jsonpath-plus
Ask Cline: "Using jsonpath-plus, help me...". 1 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add json-path-query-engine --transport http "https://edge.vinkius.com/vk_preview_7ADZSAEroKeClWEoBvRdlik7U3hNBE0F8Tuzb007/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using jsonpath-plus
Ask Claude: "Using jsonpath-plus, show me...". 1 tools are ready
Where the request belongs
Work jsonpath-plus can move forward.
This is for the backend engineer who's tired of their AI getting confused by massive API responses or the data scientist trying to keep token costs down while processing large datasets.
Backend Engineer
Extracts specific values from complex microservice responses to feed into downstream logic.
Data Analyst
Pulls specific nested fields from large JSON exports for quick summary generation.
API Integrator
Cleans up messy third-party data before passing it to an AI client.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
jmespath-query-executor
Deterministic JSON querying using simplified JMESPath syntax.
Dot-Notation Object Flattener
Convert deeply nested JSON objects into flat structures using dot-separated keys.
LLM Output JSON Extractor
Isolates valid JSON objects from mixed markdown/text LLM outputs using deterministic bracket-matching.
JSON Merge Patch
Stop losing data when updating massive files. Apply surgical JSON patches (RFC 7396) securely to large datasets.
JSONPath Query Executor
Execute deterministic JSONPath queries against any JSON data.
URL Query String Deep Parser
Transforms flat URL query strings into deeply nested JSON objects and arrays.
Bring your own AI
Change the model, client or framework. Keep jsonpath-plus connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about jsonpath-plus.
The practical details behind the request, access and result.
How does the JSON Path Query Engine help with token limits?
It extracts only the specific fields you need, which significantly reduces the amount of text sent to your AI client. This allows you to process much larger datasets without hitting context limits.
Can I use it for very large API responses?
Yes, it's designed to handle massive payloads by surgically pulling out data points instead of processing the whole file. This makes it ideal for high-volume data tasks.
Does the JSON Path Query Engine support complex nested paths?
It supports full JSONPath syntax, so you can grab deep nested values or filter arrays easily. You can target specific keys deep within a complex object structure.
Will this make my AI agent more accurate?
Yes, because the agent won't get distracted by irrelevant data in a large JSON object, it's less likely to hallucinate or misinterpret which values belong to which keys.
Is the JSON Path Query Engine good for data cleaning?
It's excellent for the extraction phase of data cleaning. By pulling out only the relevant fields from messy sources, you provide the AI with a clean, structured input.
How do I provide the query to the agent?
You just give your agent the raw JSON and the path you want to follow, such as '$.items[0].price'. The agent then uses the Connector to return only that specific data.
What JSONPath syntax is supported?
Full JSONPath Plus: root ($), deep scan (..), array indexing, filters, and recursive descent.
One connection away
Give your agent a direct line to jsonpath-plus.
Connect jsonpath-plus once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available