Provider REST API

14 actions

Connect Claude to Sentry

Find errors, inspect traces, and triage production issues. Toolspoke puts 14 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Auth token
Actions exposed: 14
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Sentry
Open the marketplace in your workspace, add Sentry to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with auth token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Sentry shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Sentry asks for

Auth token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

Auth tokenRequired: Sentry → User settings → Personal tokens. Needs event:write, project:read, and org:read.; sntryu_…
Organization slugRequired: The slug in your Sentry URL, e.g. sentry.io/organizations/acme. Every endpoint is scoped to it.; acme
Instance URLOptional: Only for self-hosted Sentry. Leave blank for sentry.io.; https://sentry.example.com

What Claude can do in Sentry

14 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 9Reads
Writes: 5Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

list_issues
Search the organization's issues, newest and most frequent first. `query` takes Sentry's own search syntax (for example `is:unresolved level:error`, `release:1.4.2`, `user.email:[email protected]`); when omitted Sentry defaults to `is:unresolved`. Start here when triaging production errors, then pass an id to get_issue or get_issue_event.
get_issue
Retrieve one issue by its numeric id or short id (e.g. ACME-3F). Returns status, assignee, counts, first and last seen, affected releases, and tag breakdowns. Long activity feeds are stripped; use get_issue_event for the stack trace.
get_issue_event
Fetch a single event for an issue, including its exception stack trace, HTTP request, tags, and runtime context. Defaults to the latest event. This is the action to call when you need to see why an error happened. Breadcrumbs are omitted unless you ask for them because they are large.
list_issue_events
List recent events for one issue so you can see how often it fires, across which releases, users, and environments. Returns event metadata only - call get_issue_event for a full payload.
list_issue_tag_values
Break one issue down by a tag - release, environment, browser, url, server_name, user - showing the most common values and how many events each accounts for. Use it to work out which release or environment introduced a regression.
get_trace
Retrieve a distributed trace by its 32-character trace id and return the span tree with any attached errors. Use it after finding a trace id on an event to see which service or query made a request slow. The tree is depth-limited to keep the response readable.
list_projects
List the organization's projects with their slugs and platforms. Call this to find the project slugs that list_issues and list_releases filter on.
list_releases
List releases newest first, with when they were deployed and how many new issues each introduced. Use it to line an error up against a deploy, and to find the version string that resolve_issue's next-release behaviour refers to.
list_members
List organization members with their emails, roles, and teams. Use it to pick a valid assignee for assign_issue.

Writes

Creates or updates something on the other side.

resolve_issue
Mark an issue as resolved immediately. Use resolve_issue_in_next_release instead when you want Sentry to reopen it if the error survives the next deploy. Reversible with reopen_issue.
resolve_issue_in_next_release
Resolve an issue in the next release: Sentry marks it resolved now and automatically reopens it if the error still occurs after the next deploy. Use resolve_issue to resolve it outright. Reversible with reopen_issue.
ignore_issue
Ignore (mute) an issue so it stops alerting. Optionally re-open it automatically after a number of minutes or once it recurs a given number of times. Reversible with reopen_issue.
reopen_issue
Move an issue back to unresolved, undoing a resolve_issue or ignore_issue.
assign_issue
Assign an issue to a person or a team. Pass a username, email, or user id for a person, or "team:<team_id>" for a team. Call list_members first if you need a valid identifier.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 14 actions above are the whole of it. A call to any other name is refused before it reaches Sentry rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
Nothing here deletes: This connector writes to Sentry, but nothing in it deletes or permanently alters anything.
It reaches no further than your credential: Toolspoke holds no access to Sentry of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Sentry: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Sentry. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Sentry's own rate limits. A call that Sentry refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Sentry?

14 named actions: 9 that only read and 5 that write. They include list_issues, get_issue and get_issue_event. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Sentry connector need?

Auth token. The connector asks for auth token and organization slug, and optionally instance url. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Sentry connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 14 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Sentry connector not do?

The 14 actions above are the whole of it. A call to any other name is refused before it reaches Sentry rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. This connector writes to Sentry, but nothing in it deletes or permanently alters anything. Toolspoke holds no access to Sentry of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Sentry. An agent has to ask. Toolspoke does not retry, queue or back off around Sentry's own rate limits. A call that Sentry refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Sentry's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Sentry?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and the credits spent. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More observability connectors

Browse all of them