Allows creating and debugging API requests in Thunder Client collections directly from GitHub Copilot Agent mode.
Click on "Deploy 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 is open source and lets your AI assistant create, update, and run Thunder Client requests and collections from plain-language prompts.
Compatible with Claude Code, Codex, GitHub Copilot, Cursor, Windsurf, and any MCP-compatible AI tool.
For requirements, installation, and setup instructions, see the Thunder Client MCP documentation.
Related MCP server: MCP-Insomnia
Issues and pull requests are welcome.
To build the server locally, run:
git clone https://github.com/thunderclient/thunderclient-mcp
cd thunderclient-mcp
npm install
npm run buildThen, in your MCP configuration, replace npx -y thunderclient-mcp with node /path/to/thunderclient-mcp/dist/index.js.
This project is open source and licensed under the MIT License.
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.
v1.0.12tc_createtc_debugScored across 2 tools
The 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.
Give your AI agents trusted access to the full Postman platform.
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Create and manage test cases, test runs and results in Testiny from your AI assistant.
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
