Is this an official Sentry MCP server?

No. It is Memtro's MCP server with Memtro's Sentry connector behind it: the connector reads Sentry through its API with the credentials you connect on Dashboard → Connections, and Sentry publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in Sentry?

Only when you ask, and only what it has been granted: resolve, archive, reopen, assign or prioritise an issue; add a note to an issue's activity; resolve, archive, reassign or reprioritise many issues at once, by id or by search; merge duplicate issues into one. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Engineering and operations

Sentry MCP server

Sentry in any MCP client, through Memtro: Sentry does not publish this server. Memtro's Sentry connector reads Sentry through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Error monitoring: search issues, read the latest event with stack trace, recent occurrences, projects and releases; can also resolve, archive, assign or prioritise an issue — one at a time, or every issue a search matches — merge duplicates into one, and add a note to an issue when you ask.

Reads

sentry_projectsList the Sentry projects in the organization (slug, platform, teams).
sentry_search_issuesSearch Sentry issues (grouped errors) in one project or across the organization using Sentry search syntax: is:unresolved (default), is:resolved…
sentry_get_issueOne issue by numeric id or short id (e.g. BACKEND-12A) with its latest event: message, culprit, tags, affected user, request…
sentry_issue_eventsRecent occurrences (individual events) of one issue, newest first: when, which environment/release/URL/browser, which user.
sentry_releasesReleases (versions) for the organization or one project, newest first: when created/deployed, new issues introduced, commit and deploy counts…

Acts, when you ask

These change something in Sentry. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

sentry_update_issueChanges a Sentry issue — resolves it, reopens it, archives (ignores) it, assigns it, or sets its priority.
sentry_comment_issueAdds a note to a Sentry issue's activity, where whoever picks the error up will read it.
sentry_bulk_update_issuesChanges up to 50 Sentry issues in ONE call — resolves, archives, reopens…
sentry_merge_issuesMerges two or more Sentry issues into one — Sentry folds the rest into whichever it picks as the parent…

Connect it

First connect Sentry on Dashboard → Connections, then add Memtro to your client once. The Sentry tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

One command registers the server; the tools are then available in every session.

claude mcp add --transport http memtro https://platform.memtro.com/api/mcp \
  --header "Authorization: Bearer sk-memtro-..."

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Sentry connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› What new errors appeared in production in the last 24 hours?
› Show me the stack trace for BACKEND-12A.
› Is the checkout timeout error still happening, and which customers hit it?
› Which release introduced the most new issues this month?

Questions

Is this an official Sentry MCP server?: No. It is Memtro's MCP server with Memtro's Sentry connector behind it: the connector reads Sentry through its API with the credentials you connect on Dashboard → Connections, and Sentry publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Sentry?: Only when you ask, and only what it has been granted: resolve, archive, reopen, assign or prioritise an issue; add a note to an issue's activity; resolve, archive, reassign or reprioritise many issues at once, by id or by search; merge duplicate issues into one. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.