Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Bug tracking and test management: issues, test cases, sprints, runs, requirements and KB.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mcp.bugasura.io/mcpRun this in your terminal
claude mcp add --transport http bugasura https://mcp.bugasura.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"bugasura": {
"url": "https://mcp.bugasura.io/mcp"
}
}
}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": {
"bugasura": {
"type": "http",
"url": "https://mcp.bugasura.io/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://mcp.bugasura.io/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
The server asks you to sign in before it lists its tools.
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 against the domain bugasura.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 250 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (3.5.1) reached the registry yesterday.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, yontu
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
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.
Connect AI assistants directly to your test management workspace.
Bugasura MCP Server enables AI tools like Claude, VS Code Copilot, and Cursor to interact with your Bugasura projects—manage test cases, track issues, plan sprints, and more—all through natural language.
| What changed | 3.4 | 3.5 |
|---|---|---|
| Starting a TestPert sprint from its requirements | bugasura_testpert_start_skip_testplan | bugasura_testpert_start_from_requirements. Same inputs and behaviour; the old name wrongly suggested it skips the test plan, which it builds |
| What changed | 3.2 | 3.3 |
|---|---|---|
| Requirement ↔ test case links | bugasura_link_unlink_requirement_testcases with is_delete | bugasura_link_requirement_testcases and bugasura_unlink_requirement_testcases (destructive); both take comma-separated testcase_ids |
| Coda, Jira, Confluence and Figma imports (10 tools) | Offered on every transport | Local (STDIO) only. They take that service's API token as an argument, so the hosted server no longer lists them and refuses calls to them |
Authentication moved to OAuth 2.0 sign-in. If you're upgrading from 2.x:
| What changed | 2.x | 3.0 |
|---|---|---|
| Hosted (HTTP) authentication | X-Bugasura-API-Key header or Authorization: Basic in the client config | Sign in from the MCP client: it opens the Bugasura login + consent page once, then refreshes tokens silently. No key in any config file. |
api_key tool parameter | Present on every tool | Removed. Tools never accept a key; the assistant must not ask for one. |
| STDIO (local subprocess) | BUGASURA_API_KEY env var | Unchanged — the env var is the only credential source for STDIO. |
| Prompt | setup_api_key | connect_bugasura |
| Server requirements (HTTP) | none | MCP_PUBLIC_BASE_URL, BUGASURA_OAUTH_CLIENT_ID, BUGASURA_OAUTH_CLIENT_SECRET (see *Deploying the OAuth sign-in*) |
If you're upgrading from 1.x, update your client configuration:
| What changed | 1.x | 2.0 |
|---|---|---|
| Tool names | create_issue, list_teams, … | bugasura_create_issue, bugasura_list_teams, … (prefixed to coexist with other MCP servers) |
| Default HTTP endpoint | /sse (SSE) | /mcp (streamable HTTP) |
| List/find responses | {status, project_list, …} (upstream shape) | Standard pagination envelope {status, total, count, offset, items, has_more, next_offset} — legacy keys remain as extras for one release |
1.x clients pointed at /sse must migrate to /mcp — SSE has been removed.
That's all the hosted server needs. On first use your AI tool opens the Bugasura sign-in page in your browser; approve once and you're connected. Tokens refresh automatically for 30 days.
An API key is only needed for the local STDIO setup described under *Local Development*.
Add the server URL to your AI tool. No headers, no keys: the client discovers the OAuth sign-in from the server and walks you through it.
Claude Desktop
Open Claude Desktop → Settings → Connectors → Add Custom Connector
Bugasurahttps://mcp.bugasura.io/mcpClick Connect, sign in to Bugasura, and click Allow on the consent page.
VS Code
Install in VS Code, or add to your VS Code MCP config:
{
"servers": { "bugasura": { "type": "http", "url": "https://mcp.bugasura.io/mcp" } } }
VS Code detects the OAuth sign-in and opens the browser the first time a tool is used.
Claude Code
claude mcp add --transport http bugasura https://mcp.bugasura.io/mcp
Then run /mcp inside Claude Code, choose Bugasura → Authenticate, and complete the sign-in in the browser.
ChatGPT
Settings → Apps & Connectors → Advanced → turn on Developer mode, then Create:
Bugasurahttps://mcp.bugasura.io/mcpClick Create, sign in to Bugasura, and click Allow.
Codex
codex mcp add bugasura --url https://mcp.bugasura.io/mcp
codex mcp login bugasura
Cursor
Add to Cursor, or add to ~/.cursor/mcp.json:
{
"mcpServers": { "bugasura": { "url": "https://mcp.bugasura.io/mcp" } } }
Cursor shows a Needs login badge next to the server; click it to sign in.
Windsurf
Add to your Windsurf MCP config:
{
"mcpServers": { "bugasura": { "serverUrl": "https://mcp.bugasura.io/mcp" } } }
Windsurf opens the sign-in page on first use.
Cline
{
"mcpServers": { "bugasura": { "url": "https://mcp.bugasura.io/mcp", "type": "streamableHttp" } } }
Roo Code
{
"mcpServers": { "bugasura": { "type": "streamable-http", "url": "https://mcp.bugasura.io/mcp" } } }
Once installed, just talk naturally to your AI assistant:
"List all my Bugasura teams and projects"
"Create a test case for login functionality with high severity"
"Create a requirement for user authentication feature"
"Show me all critical bugs in sprint 5"
Bugasura MCP features interactive context selection. You don't need to know team IDs, project IDs, or user IDs—just describe what you want in natural language.
Example: Creating an issue without knowing any IDs:
You: "Create a bug for the login button not working"
AI: [Calls MCP server] "Which team should I use?
You: "Acme Corp"
AI: "Which project?
You: "Mobile App"
AI: "Which sprint?
You: "Sprint 5"
AI: ✓ "Created issue #ISSUE-123 in Sprint 5"
The system guides you through team → project → sprint selection automatically.
Assign work using names, emails, or user IDs—the system automatically converts them:
"Assign issue 123 to John Doe"
"Add jane@example.com and user 789 to issue 456"
"Remove Sarah from issue 321"
Works for both issues and test cases.
Find resources without memorizing IDs:
"Find my mobile app project"
→ Searches across ALL teams automatically
"Show me all projects I have access to" → Returns complete context in one call
Create an API test case for user authentication with priority P1
List all test cases for the mobile app project
Update test case 123 to mark it as PASS
Assign test case 456 to john@example.com
Delete test case 789
Delete test case with key "TES5"
Delete test case named "Verify login with valid credentials"
List all comments on test case 123
List comments on test case "Verify login with valid credentials"
List only user comments on test case 456 (exclude system comments)
Get details of comment 789
Add a comment "Test passed on Chrome and Firefox" to test case 123
Add a private comment to test case 456
Update comment 789 with new text
Delete comment 456
Create a requirement titled "User Authentication" with details and priority P1
List all requirements for the mobile app project
Get requirement details for requirement ID 2036
Update requirement 2036 to change severity to HIGH
Assign requirement 456 to john@example.com
Create a folder named "Sprint 1 Features" for organizing requirements
List all requirement folders in a project
Delete requirement 789
Link test cases to requirement 2036
Create a critical bug for login page crash in sprint 5
Show me all open issues assigned to me
Update issue 789 to change status to "Fixed"
Add John and Jane as assignees to issue 123
Delete issue 456
Delete issue with key "ISS09"
Delete issue with summary "Login button not working"
List all comments on issue 123
List comments with pagination (start at 10, show 20 results)
List only user comments, exclude system comments
Get details of comment 456
Add a comment "Fixed in latest build" to issue 789
Add a private comment to issue 123
Update comment 456 with new text
Delete comment 789
Create a new sprint called "Sprint 15" for the mobile app
List all sprints for project 456
Update sprint 789 to mark it as COMPLETED
Show sprint details including issue statistics
Delete sprint 321
Only the beginning is shown; read the rest in the repo