bugsmash-mcp
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., "@bugsmash-mcp show me my recent BugSmash reviewer feedback"
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.
BugSmash MCP
Local Model Context Protocol server that lets an LLM read and manage BugSmash reviewer feedback without ever seeing your BugSmash API key.
LLM (Claude) --MCP--> bugsmash-mcp --HTTPS + X-API-Key--> https://api.bugsmash.io/api/v2Install
npm install -g @mxrcochxvez/bugsmash-mcpOr run without a global install via npx (see connector config below).
Requires Node.js 18+.
Related MCP server: Gerrit MCP Server
Generate an API key
Sign in at tools.bugsmash.io.
Open your profile menu → Settings.
Find the API Key section and copy the key.
Treat it like a password. If it leaks, regenerate it immediately from the same settings page.
Official auth docs: docs.bugsmash.io/authentication
Set BUGSMASH_API_KEY (do not commit it)
Export the key in your shell — never put it in a committed file.
export BUGSMASH_API_KEY="your-key-here"macOS / Linux (zsh), persist for your user:
echo 'export BUGSMASH_API_KEY="your-key-here"' >> ~/.zshrc
source ~/.zshrcConfirm it is set (does not print the value):
test -n "$BUGSMASH_API_KEY" && echo "BUGSMASH_API_KEY is set"Register as a user-level MCP connector
Use a user scope so the server is available in every project.
Claude Code / Claude CLI (recommended: npx)
claude mcp add --scope user bugsmash --env BUGSMASH_API_KEY=$BUGSMASH_API_KEY -- npx -y @mxrcochxvez/bugsmash-mcpIf you installed globally:
claude mcp add --scope user bugsmash --env BUGSMASH_API_KEY=$BUGSMASH_API_KEY -- bugsmash-mcpClaude Desktop
Edit your Claude Desktop config (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"bugsmash": {
"command": "npx",
"args": ["-y", "@mxrcochxvez/bugsmash-mcp"],
"env": {
"BUGSMASH_API_KEY": "your-key-here"
}
}
}
}Prefer injecting the key from the environment your Desktop app inherits, rather than pasting it into a synced config file when possible.
Cursor
Add a similar MCP entry: command npx, args ["-y", "@mxrcochxvez/bugsmash-mcp"], and BUGSMASH_API_KEY under env.
Tools
Tool | BugSmash API | Purpose |
|
| Paginated project list (find |
|
| Project details + versions |
|
| All reviewer comments on a project |
|
| Single comment (+ replies) |
|
| Update text / status / priority / privacy |
|
| Thread replies |
|
| Reply on a thread |
Base URL: https://api.bugsmash.io/api/v2
Auth header: X-API-Key (never a tool argument).
Typical flow: list_projects → list_feedback → optionally update_feedback / post_reply.
Security note
The API key is read only from
BUGSMASH_API_KEY.It is never accepted as a tool parameter.
It must never be logged, printed, masked-partially in errors, or returned in tool responses.
On startup, a missing key exits with the generic message
BUGSMASH_API_KEY is not set.All HTTP calls go through one helper that attaches
X-API-Key; request headers are not surfaced on errors.
Local development
git clone https://github.com/mxrcochxvez/bugsmash_mcp.git
cd bugsmash_mcp
npm install
npm run build
export BUGSMASH_API_KEY="your-key-here"
npm startnpm run typecheck # tsc --noEmit
npm run pack:check # preview files included in the npm tarballAPI reference: docs.bugsmash.io
Available Tools
7 toolsget_feedbackGet BugSmash commentA
Fetch a single comment by UUID, including replies when present. Maps to GET /comment/{commentId}.
Inputs: commentId (required), plainText, locationMetadata.
get_projectGet BugSmash projectA
Fetch details for a single BugSmash project, including versions and review links. Maps to GET /project/{projectId}.
Inputs: projectId (required).
list_feedbackList BugSmash feedbackA
Retrieve all reviewer comments for a project. Maps to GET /comments?projectId. Prefer plainText=true for LLM consumption. Optionally include location metadata (pin/DOM/page).
Inputs: projectId (required), status, plainText, locationMetadata.
list_projectsList BugSmash projectsA
List review projects in the BugSmash workspace (paginated). Use this to discover project IDs before calling list_feedback. Maps to GET /projects.
Inputs: page, limit, types, folderId.
list_repliesList comment repliesA
List all replies on a comment thread. Maps to GET /comment/{commentId}/replies.
Inputs: commentId (required), plainText.
post_replyReply to a BugSmash commentB
Post a reply on an existing comment thread. Maps to POST /reply.
Inputs: text (required), commentId (required), isPrivate.
update_feedbackUpdate BugSmash commentA
Update a comment's text, status (e.g. mark Resolved), priority, or privacy. Maps to PATCH /comment/{commentId}. At least one field besides commentId is required.
Inputs: commentId (required), text, status, priority, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct resource and action: projects vs comments vs replies, and list/get vs update/post. No two tools overlap in purpose, making selection unambiguous.
All tool names follow a consistent verb_noun pattern (list_projects, get_project, get_feedback, list_feedback, update_feedback, list_replies, post_reply), with no stylistic deviations.
With 7 tools, the server is well-scoped for its purpose. Each tool is necessary and non-redundant, covering project discovery, feedback retrieval/update, and reply management.
The tool set provides complete coverage for the domain: discover projects, fetch project details, list/get feedback, update feedback, and manage reply threads. No critical operations are missing for the intended workflow.
Maintenance
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
Related MCP Servers
- AlicenseAqualityDmaintenanceA MCP server for interacting with FogBugz issue tracker through LLMs such as Claude. Supports both the XML API (/api.asp) and the JSON API (/f/api/0/jsonapi) with automatic version detection at startup. Works with on-premise and on-demand FogBugz installations.192MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables language models to query and manage Gerrit code reviews via the REST API.78 PyPI1Apache 2.0
- AlicenseAqualityDmaintenanceMCP server that exposes code review tasks from the Fix My Comments VS Code extension to AI agents, enabling them to list, retrieve, reply to, and update task statuses.44 npmMIT
- AlicenseNot gradedqualityAmaintenanceMCP server for Open Feedback, enabling AI assistants to submit, list, get, update status of, and analyze product feedback via a local HTTP API and JSONL storage.346 npmApache 2.0