Rollbar
Access Rollbar project data for error monitoring and debugging.
rollbar-mcp-server
A Model Context Protocol (MCP) server for Rollbar.
[!NOTE] This software is alpha quality and under active development.
Features
This MCP server implementes the stdio server type, which means your AI tool (e.g. Claude) will run it directly; you don't run a separate process or connect over http.
Configuration
ROLLBAR_ACCESS_TOKEN: an access token for your Rollbar project with read and/or write scope.
Tools
get-item-details(counter, max_tokens?): Given an item number, fetch the item details and last occurrence details. Supports an optional max_tokens parameter (default: 20000) to automatically truncate large occurrence responses. Example prompt: Diagnose the root cause of Rollbar item #123456
get-deployments(limit): List deploy data for the given project. Example prompt: List the last 5 deployments or Are there any failed deployments?
get-version(version, environment): Fetch version details for the given version string, environment name, and the configured project.
get-top-items(environment): Fetch the top items in the last 24 hours given the environment name, and the configured project.
list-items(environment): List items filtered by status, environment and a search query.
get-replay(environment, sessionId, replayId, delivery?): Retrieve session replay metadata and payload for a specific session in the configured project. By default the tool writes the replay JSON to a temporary file (under your system temp directory) and returns the path so any client can inspect it. Set delivery="resource" to receive a rollbar://replay/<environment>/<sessionId>/<replayId> link for MCP-aware clients. Example prompt: Fetch the replay 789 from session abc in staging.
update-item(itemId, status?, level?, title?, assignedUserId?, resolvedInVersion?, snoozed?, teamId?): Update an item's properties including status, level, title, assignment, and more. Example prompt: Mark Rollbar item #123456 as resolved or Assign item #123456 to user ID 789. (Requires write scope)
How to Use
Tested with node 20 and 22 (nvm use 22).
Claude Code
Configure your .mcp.json as follows:
{
"mcpServers": {
"rollbar": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@rollbar/mcp-server@latest"
],
"env": {
"ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
}
}
}
}
Codex CLI
Add to your ~/.codex/config.toml:
[mcp_servers.rollbar]
command = "npx"
args = ["-y", "@rollbar/mcp-server@latest"]
env = { "ROLLBAR_ACCESS_TOKEN" = "<project read/write acecss token>" }
Junie
Configure your .junie/mcp/mcp.json as follows:
{
"mcpServers": {
"rollbar": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@rollbar/mcp-server@latest"
],
"env": {
"ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
}
}
}
}
VS Code
Configure your .vscode/mcp.json as follows:
{
"servers": {
"rollbar": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@rollbar/mcp-server@latest"
],
"env": {
"ROLLBAR_ACCESS_TOKEN": "<project read/write access token>"
}
}
}
}
Or using a local development installation - see CONTRIBUTING.md.
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Makefile MCP Server
Exposes Makefile targets as callable tools for AI assistants.
Auto API - YApi
A tool to retrieve API interface information from YApi, with authentication configurable via environment variables.
MCP Simple OpenAI Assistant
A simple server for interacting with OpenAI assistants using an API key.
WinTerm MCP
Provides programmatic access to the Windows terminal, enabling AI models to interact with the command line interface.
Lenses
Manage, explore, transform and join data across multiple clusters using different flavours of Apache Kafka via Lenses.io (including the free Community Edition)
Openapi MCP
An MCP server that lets LLMs inspect and interact with OpenAPI specifications.
Code Editor
Enables AI assistants to write, edit, and manage code files directly in a specified directory, respecting .gitignore patterns.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
Semgrep
Static code analysis using Semgrep for security vulnerability detection and code quality improvements.
Remote MCP Server on Cloudflare
An MCP server deployable on Cloudflare Workers with OAuth login support.