Sentrycompanionmcp MCP Server

Unofficial Sentry MCP that provide unavailable tools on the official MCP.

Local serverstdio

What is the Sentrycompanionmcp MCP server?

Sentrycompanionmcp MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Unofficial Sentry MCP that provide unavailable tools on the official MCP.

What the assistant can call

Once Sentrycompanionmcp is connected, these are the calls the assistant has available:

  • get_release_health — CFU, crash-free sessions, session and user counts for a release
  • get_release_adoption — Session-based and user-based adoption %
  • compare_releases — Side-by-side CFU comparison between two releases
  • get_release_new_issues — Issues first seen in a specific release
  • get_release_regressed_issues — Issues that regressed in a specific release
  • get_release_deploys — Deployment history for a release
  • add_issue_comment — Post a comment on a Sentry issue

Configuration and credentials

You will need 4 environment variables: SENTRY_PERSONAL_TOKEN, SENTRY_ORG, SENTRY_PROJECT, SENTRY_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Installation goes through your MCP client rather than a global install: point it at sentry-companion-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Choosing this one

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Sentrycompanionmcp's toolset — get_release_health, get_release_adoption, compare_releases and 4 more — is a fair guide to whether it matches your workflow. It is maintained by agimaulana; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Sentrycompanionmcp's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the sentrycompanionmcp mcp server does with a few real requests.

Available tools

ToolWhat it does
get_release_healthCFU, crash-free sessions, session and user counts for a release
get_release_adoptionSession-based and user-based adoption %
compare_releasesSide-by-side CFU comparison between two releases
get_release_new_issuesIssues first seen in a specific release
get_release_regressed_issuesIssues that regressed in a specific release
get_release_deploysDeployment history for a release
add_issue_commentPost a comment on a Sentry issue

How to install the Sentrycompanionmcp MCP server

Or add manually to your `.mcp.json`:

```json
{
  "mcpServers": {
    "sentry-companion": {
      "type": "stdio",
      "command": "uvx",
      "args": ["sentry-companion-mcp"],
      "env": {
        "SENTRY_PERSONAL_TOKEN": "your_token",
        "SENTRY_ORG": "your-org-slug",
        "SENTRY_PROJECT": "your-project-id",
        "SENTRY_BASE_URL": "https://us.sentry.io"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SENTRY_PERSONAL_TOKENCredential the server authenticates with.Yes
SENTRY_ORGConfiguration value read at startup.Optional
SENTRY_PROJECTConfiguration value read at startup.Optional
SENTRY_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Sentrycompanionmcp to get release health.
  • Use Sentrycompanionmcp to get release adoption.
  • Use Sentrycompanionmcp to compare releases.

Frequently asked questions

It connects Sentrycompanionmcp to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (get_release_health, get_release_adoption, compare_releases, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Sentrycompanionmcp directly.