Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
MCP server mode for Qoder CLI — delegate coding tasks to local Qoder agents from any MCP client.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
QODERCLI_PATH, QODERCLI_DEFAULT_PERMISSION_MODE, HTTP_PROXY, HTTPS_PROXYYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"qodercli": {
"command": "npx",
"args": [
"-y",
"qodercli-mcp"
],
"env": {
"QODERCLI_PATH": "your-value",
"QODERCLI_DEFAULT_PERMISSION_MODE": "your-value",
"HTTP_PROXY": "your-value",
"HTTPS_PROXY": "your-value"
}
}
}
}Run this in your terminal
claude mcp add qodercli --env QODERCLI_PATH=your-value --env QODERCLI_DEFAULT_PERMISSION_MODE=your-value --env HTTP_PROXY=your-value --env HTTPS_PROXY=your-value -- npx -y qodercli-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"qodercli": {
"command": "npx",
"args": [
"-y",
"qodercli-mcp"
],
"env": {
"QODERCLI_PATH": "your-value",
"QODERCLI_DEFAULT_PERMISSION_MODE": "your-value",
"HTTP_PROXY": "your-value",
"HTTPS_PROXY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"qodercli": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"qodercli-mcp"
],
"env": {
"QODERCLI_PATH": "your-value",
"QODERCLI_DEFAULT_PERMISSION_MODE": "your-value",
"HTTP_PROXY": "your-value",
"HTTPS_PROXY": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
QODERCLI_PATH envQODERCLI_DEFAULT_PERMISSION_MODE envHTTP_PROXY envHTTPS_PROXY envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account cantbeblank96, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.4.3) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
English | 简体中文
The missing MCP server mode for Qoder CLI — delegate coding tasks to local Qoder agents from any MCP client (Qoder IDE, Claude Code, Cursor…).
A minimal MCP server that wraps the local qodercli (Qoder CLI) as MCP tools, letting any MCP client (Qoder IDE, Claude Code, Cursor, …) call Qoder like a sub-agent.
*30s demo: MCP client ⇄ qodercli-mcp ⇄ qodercli — initialize → tools/list → list-models (real output, not sped up)*
Zero-config via npx — add this to your MCP client config (~/.qoder/mcp.json, claude_desktop_config.json, …):
{ "mcpServers": { "qodercli-mcp": { "command": "npx", "args": ["-y", "qodercli-mcp"] } } }
Three tools are exposed:
| Tool | Purpose |
|---|---|
ask-qoder | Delegate a task to qodercli |
list-sessions | Discover resumable sessions |
list-models | Runtime model discovery |
Highlights: verified permission semantics (see below — e.g. dont_ask is read-only), codex-style sandbox/approval_policy, structured output (session_id/duration_ms/total_credits).
Full configuration options are in Install.
Some CLI agents ship an official MCP server mode (e.g. codex mcp-server), but qodercli currently only acts as an MCP client. This project fills that gap with a thin wrapper: it spawns qodercli -p under the hood and streams the result back over MCP stdio.
ask-qoder tool — delegate a prompt to qoderclisession_id, is_error, duration_ms, total_credits, num_turns) via -o json parsinglist-sessions tool to discover resumable sessionslist-models tool for runtime model discovery (no stale model lists)reasoning_effort parameter (--reasoning-effort)instructions in the MCP initialize result guide clients on usagesandbox levels (read-only / workspace-write / danger-full-access)system_prompt / append_system_prompt)resume_session_id) for multi-turn delegationHTTP_PROXY / HTTPS_PROXY injection)qodercli installed and signed in (qodercli login)Option A — npx (recommended): no clone needed, the MCP client downloads the package on first use.
"command": "npx", "args": ["-y", "qodercli-mcp"]
Option B — from source (for development):
git clone https://github.com/cantbeblank96/qodercli-mcp.git
cd qodercli-mcp npm install
Add to ~/.qoder/mcp.json. Prefer the absolute path of node and set QODERCLI_PATH explicitly (nvm-managed binaries are often missing from the PATH seen by MCP child processes):
Proxy Support: To use your Qoder CLI proxy quota, add
HTTP_PROXYand/orHTTPS_PROXYto the server's environment. When these are set at the MCP server level, they will be passed to all qodercli subprocesses.
{
"mcpServers": { "qodercli-mcp": { "command": "npx", "args": ["-y", "qodercli-mcp"], "env": { "QODERCLI_PATH": "/absolute/path/to/qodercli", "PATH": "/usr/local/bin:/usr/bin:/bin" } }, "qodercli-mcp-with-proxy": { "command": "npx", "args": ["-y", "qodercli-mcp"], "env": { "QODERCLI_PATH": "/absolute/path/to/qodercli", "HTTP_PROXY": "http://127.0.0.1:39900", "HTTPS_PROXY": "http://127.0.0.1:39900", "PATH": "/usr/local/bin:/usr/bin:/bin" } } } }
Developers running a local checkout instead of the published package (Option B) should replace command/args with the absolute node path and /path/to/qodercli-mcp/src/index.js (nvm-managed node is often missing from the PATH seen by MCP child processes).
{
"mcpServers": { "qodercli-mcp": { "command": "node", "args": ["/absolute/path/to/qodercli-mcp/src/index.js"], "env": { "QODERCLI_PATH": "/absolute/path/to/qodercli" } } } }
ask-qoder| Parameter | Type | Description | ||||
|---|---|---|---|---|---|---|
prompt | string (required) | The task or question for qodercli | ||||
cwd | string | Working directory | ||||
model | string | Model for this session; call list-models to discover available names | ||||
reasoning_effort | string | Reasoning effort level (--reasoning-effort), e.g. low/medium/high; depends on the model | ||||
permission_mode | enum | dont_ask (default, read-only) \ | accept_edits (auto-approve file edits) \ | bypass_permissions (full access incl. shell) \ | auto \ | default; mutually exclusive with approval_policy, prefer sandbox |
approval_policy | enum | codex-style: untrusted→read-only \ | on-request→auto \ | never→full access | ||
sandbox | enum | read-only \ | workspace-write \ | danger-full-access (codex-style; controls the effective permission mode) | ||
system_prompt | string | Replace the default system prompt | ||||
append_system_prompt | string | Append instructions to the default system prompt | ||||
resume_session_id | string | Resume a previous session | ||||
output_format | string | Passed to -o (default json). Note: non-json formats degrade structured output (session_id etc. become unavailable) | ||||
extra_args | string[] | Raw CLI args appended before the prompt; reserved flags (permission mode, system prompt, model, -o, -r, -w...) are rejected | ||||
timeout_ms | number | Timeout in ms, default 600000 |
ask-qoder declares an MCP outputSchema and returns, in addition to the human-readable text, a structuredContent object:
{
"session_id": "77826b5c-...", // pass back as resume_session_id "content": "OK", "is_error": false, "exit_code": 0, "duration_ms": 1280, "total_credits": 0.53, "num_turns": 1, "timed_out": false, "truncated": false }
| sandbox | Effective permission mode | Effect on qodercli |
|---|---|---|
| (omitted) | dont_ask | Read-only: permission-requiring tools are silently denied |
read-only | dont_ask | Plus --disallowed-tools write_file,replace,run_shell_command as defense in depth |
workspace-write | accept_edits | Agent can create/modify files in cwd |
danger-full-access | bypass_permissions | Full access including shell |
Explicit permission_mode or approval_policy always wins over sandbox.
| Mode | Behavior |
|---|---|
dont_ask | Read-only: silently denies every tool call that requires permission. Headless-safe default |
accept_edits | Auto-approves file edits; shell still governed by policy |
bypass_permissions | Auto-approves everything including shell |
auto | qodercli's own automatic policy |
default | Interactive confirmation — not headless-friendly, avoid in MCP calls |
list-sessionsLists local qodercli sessions (index, summary, session id) so a client can pick a resume_session_id. Takes no arguments.
list-modelsLists models currently supported by qodercli (via --list-models), so a client can pick a valid model value at runtime instead of relying on stale knowledge. Returns both a text list and a structured models array. Takes no arguments.
{ "name": "ask-qoder", "arguments": {
"prompt": "Explain what main.py does", "cwd": "/path/to/project", "timeout_ms": 180000 }}
{ "name": "ask-qoder", "arguments": {
"prompt": "@src/service.py Review this file for security issues and suggest improvements", "model": "qwen-plus", "permission_mode": "dont_ask", "timeout_ms": 300000 }}
// First call — session_id comes back in structuredContent
{ "name": "ask-qoder", "arguments": { "prompt": "Help me refactor this module to improve readability", "cwd": "/projects/backend", "timeout_ms": 300000 }} // Then reuse structuredContent.session_id: { "name": "ask-qoder", "arguments": { "prompt": "Now add error handling for database timeouts", "resume_session_id": "77826b5c-cd6b-4213-b423-d95b4e1deab0" }} // Or discover ids with list-sessions { "name": "list-sessions", "arguments": {} }
{ "name": "ask-qoder", "arguments": {
"prompt": "Analyze performance bottlenecks in utils.py", "model": "qwen-max", "permission_mode": "default", "output_format": "text", "timeout_ms": 240000 }}
{ "name": "ask-qoder", "arguments": {
"prompt": "Audit this codebase for security issues; do not modify anything", "cwd": "/workspaces/repo", "sandbox": "read-only", "timeout_ms": 300000 }}
`read-only` disables write/shell tools — good for audits and reviews.
{ "name": "ask-qoder", "arguments": {
"prompt": "Summarize the architecture of this project and identify key modules", "cwd": "/workspaces/repo", "timeout_ms": 420000, "model": "qwen-plus" }}
cwd when operating on a specific projecttimeout_ms shorter than 60minresume_session_id instead of repeating contextlist-models first to discover currently supported models; larger models are better for deep analysisdont_ask); set QODERCLI_DEFAULT_PERMISSION_MODE=bypass_permissions to make full (YOLO) access the default for personal deployments. Per-call: tasks that must create/modify files need sandbox: "workspace-write"; shell access needs danger-full-access. Do not combine sandbox with an explicit permission_mode (the latter wins)| Variable | Default | Description |
|---|---|---|
QODERCLI_PATH | qodercli | Path to the qodercli binary |
QODERCLI_TIMEOUT_MS | 600000 | Default timeout |
QODERCLI_MAX_OUTPUT_MB | 50 | Per-call stdout/stderr cap in MB (OOM protection) |
QODERCLI_DEFAULT_PERMISSION_MODE | dont_ask | Default permission mode when the caller omits permission_mode/approval_policy/sandbox; set bypass_permissions for full (YOLO) access |
HTTP_PROXY | - | HTTP proxy URL for qodercli |
HTTPS_PROXY | - | HTTPS proxy URL for qodercli |
npm test # smoke test: protocol handshake + tool invocation
node src/index.js # run the server manually (stdio)
This is an unofficial, third-party tool. It is not affiliated with, endorsed, or sponsored by Qoder. Use permission_mode: bypass_permissions with care — delegated prompts may modify files in the target working directory.
Main gall
Only the beginning is shown; read the rest in the repo