Allows creating and debugging API requests in Thunder Client collections directly from GitHub Copilot Agent mode.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@thunderclient-mcp Get endpoints from my project and save to a collection called 'My API'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The Thunder Client MCP server enables customers to integrate with AI tools to create requests and collections. It is compatible with various AI development environments, including Cline, Continue.dev, and GitHub Copilot.
A Business or Enterprise plan subscription is required to use the Thunder Client MCP Server.
View Thunder Client pricing plans here.
Related MCP server: Istek MCP Server
This MCP server provides three powerful tools for managing Thunder Client operations:
tc_createDescription:
Saves API endpoints to Thunder Client, automatically creating collections and folders if they do not already exist.
Usage:
Use AI to analyze your current project and automatically generate API requests in Thunder Client, with the appropriate collection and folder created as needed.
Add new requests to a specific collection in Thunder Client.
Dynamically create a request using an AI-generated prompt.
tc_debugDescription: Show Thunder Client CLI debug information using tc --debug in the given project directory.
Usage: Troubleshoot and get detailed debug information from Thunder Client
Open Cline and navigate to the MCP Server section
Click on Installed
Click on Configure the MCP Server
Add the following configuration inside the mcpServers JSON:
{
"mcpServers": {
"thunderclient": {
"name": "Thunder Client MCP Server",
"type": "stdio",
"command": "npx",
"args": ["-y", "thunderclient-mcp"]
}
}
}Important: Replace thunderclient-mcp with /path/to/thunder-mcp/dist/index.js with your actual index.js location in local Dev mode.
Once configured, you can use all tc_* command tools in Cline's MCP interface.
Add a new MCP server to your configuration
Switch to Agent mode instead of Chat mode
Configure using the following YAML structure:
name: Thunder Client MCP Server
version: 0.0.1
schema: v1
mcpServers:
- name: Thunder Client MCP Server
command: npx
args:
- thunderclient-mcpImportant: Replace thunderclient-mcp with /path/to/thunder-mcp/dist/index.js with your actual index.js location in local Dev mode.
Switch to Agent mode from Chat mode
Click on the Tools icon in the interface
Scroll down and click + Add more tools
Select + Add MCP Server
Choose Stdio as the connection type
Enter the command to run as npx thunderclient-mcp
Enter the mcp name thunderclient-mcp-server-....
Choose where to install MCP, select Global or User
Save the configuration
Important: Replace npx thunderclient-mcp with node /path/to/thunder-mcp/dist/index.js with your actual index.js location in local Dev mode.
This document contains simple example prompts for the tc_create tool to extract APIs from code files and save them to Thunder Client.
"Get the endpoints from the current project and save them with collection name 'My API' using Thunder Client MCP.""Get the endpoints from app/main.py and save them with collection name 'E-commerce API' and folder name 'Products' using Thunder Client MCP.""Get the endpoints from the src/routes/ folder and save them with collection name 'Node API' using Thunder Client MCP.""Create a POST request to https://api.example.com/users with a JSON body and an Authorization header using Thunder Client MCP."npm i
npm run buildAfter building, a dist folder will be created. Copy the index.js path from the dist folder - this path will be used in your MCP server configuration.
Use Attach Context: Utilize the Attach Context option in your AI environment
Attach Required Files: Include relevant files and specifically attach the tc_create tool context
Provide Clear Prompts: Give detailed, specific prompts to assist with command execution
Path Issues: Ensure all file paths are absolute and correctly formatted for your operating system
Node.js Version: Verify you're using a compatible Node.js version
Permissions: Check that the MCP server has appropriate file system permissions
Project Directory: Ensure the projectDir parameter points to a valid Thunder Client workspace
Feel free to contribute to this project by submitting issues or pull requests to improve functionality and compatibility with different AI development environments.
Create API endpoints to Thunder Client, automatically creating collections and folders if they do not already exist.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must cover behavior. It mentions auto-creating collections and folders, which is useful, but omits details on idempotency, conflict handling, or error states. The mutation nature is implied but not explicitly safe or destructive.
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 conveying the core action and a key behavioral detail (auto-creation). No redundant words; efficient and front-loaded.
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 tool with no parameters and no output schema, the description covers the basic purpose and a behavioral trait. However, it lacks explanation of how the tool operates without input (e.g., contextual defaults) and does not mention return values or side effects beyond folder creation.
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?
No parameters exist, so schema coverage is 100%. The description adds context by stating the tool creates endpoints and auto-creates collections/folders, but the vagueness of 'API endpoints' limits added value beyond the empty schema.
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 verb 'Create' and resource 'API endpoints to Thunder Client' are clear. The mention of automatic collection/folder creation adds specificity. However, without parameters, it's unclear how the tool determines what to create, which slightly reduces clarity.
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 the sibling 'tc_debug'. The description lacks context on prerequisites or alternatives, leaving the agent to infer usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Runs the Thunder Client debug command and display the result.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description gives minimal behavioral information. It mentions 'display the result' but does not disclose side effects, state changes, or any other traits beyond the basic action.
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 concise sentence with no fluff, but it is somewhat underspecified. It earns its place but could be slightly improved with more context.
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 the simplicity (no parameters, no output schema, no annotations), the description is adequate but incomplete. For a debug tool, more information about expected output or behavior would be beneficial.
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?
With zero parameters and 100% schema coverage, the description adds nothing beyond the schema. Baseline of 4 is appropriate for a no-parameter tool.
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 it runs a debug command and displays results, with a specific verb and resource. It distinguishes from the sibling 'tc_create' which likely creates something, but the term 'debug command' is somewhat vague.
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. It only describes what it does without any context on typical use cases or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.12tc_createtc_debugThe two tools have clearly distinct purposes: one creates API endpoints and handles collection/folder creation, the other runs a debug command. No overlap or ambiguity.
Both tools follow a consistent 'tc_verb' naming pattern with clear verbs ('create' and 'debug'), making it predictable for an agent.
Only 2 tools for a server managing API endpoints is very limited. A typical CRUD surface would require at least 5-8 tools (list, get, create, update, delete, debug, etc.).
The tool surface covers only creation and debugging. Critical operations like listing, updating, deleting endpoints or managing collections/folders are missing, leaving significant gaps for common workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Give your AI agents the tools to build, manage, and run automation workflows.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thunderclient/thunderclient-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
