io.github.thuupx/lunge
Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
lunge-mcpclaude mcp add lunge -- npx -y lunge-mcp@1.3.1{
"mcpServers": {
"lunge": {
"command": "npx",
"args": [
"-y",
"lunge-mcp@1.3.1"
]
}
}
}Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
lunge
An agent-native advanced API client - execute and test REST, GraphQL, WebSocket, SSE, and (later) gRPC requests from any MCP-capable AI agent. No GUI, no manual clicking, no heavyweight desktop app. Think advanced curl, native for agents.
It is a lightweight, token-efficient alternative to Postman/Bruno for the era of AI coding agents. The agent calls tools directly; there are no humans in the loop and no bloated feature surface to pay for.
Why this exists
| Pain with Postman/Bruno | lunge approach |
|---|---|
| Require human clicking in a GUI | Agent-native: everything is an MCP tool call |
| Postman is heavy, enterprise features are paywalled | Small, open, single local binary + thin MCP layer |
| Verbose responses blow up the LLM context window | Rust core summarizes/compresses output before it reaches the agent |
| Collections are locked into proprietary formats | Plain YAML/JSON files, git-friendly |
| Separate tools per protocol | One server for REST/GraphQL/WS/SSE/gRPC |
Design pillars
- Agent-native - designed for LLM tool calls, not human UIs.
- Token-efficient - every response is filtered, truncated, and summarized. Full payloads are spilled to disk and referenced by handle so the context stays small.
- Fast & portable - a Rust core (execution + protocols + summarization) exposed to a thin TypeScript MCP layer via napi-rs.
- Both ad-hoc and reusable - agents can fire one-off requests or create, save, and re-run declarative collections stored as files.
Documents
| Doc | Contents |
|---|---|
| architecture.md | System design, the Rust/TS split, module layout, streaming strategy, FFI boundary |
| features.md | Full feature list by protocol + cross-cutting features (auth, vars, assertions, token optimizer) |
| mcp-tools.md | The MCP tool surface: names, inputs, outputs, examples |
| collection-format.md | The declarative YAML/JSON test/collection format |
| roadmap.md | Phased delivery plan from scaffolding to gRPC and CI |
Decisions locked in
- Stack: Rust core via napi-rs + TypeScript MCP layer (
@modelcontextprotocol/sdk). - Distribution: local dev tool over stdio transport (used by Cursor/Windsurf/Claude Desktop).
- Test definition: both ad-hoc agent calls and persisted declarative collections.
- MVP protocols: REST, GraphQL, WebSocket, SSE. gRPC is a later phase.
Questions fréquentes
Qu'est-ce que io.github.thuupx/lunge ?
Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections
Comment installer io.github.thuupx/lunge ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add lunge -- npx -y lunge-mcp@1.3.1. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour io.github.thuupx/lunge ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
io.github.thuupx/lunge est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient io.github.thuupx/lunge ?
Il est publié par thuupx. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.