Skip to main content

Announcing StackOne Defender: leading open-source prompt injection guard for your agent Read More

Sentry MCP Server
for AI Agents

Production-ready Sentry MCP server with 74 extensible actions — plus built-in authentication, security, and optimized execution.

Sentry logo
Sentry MCP Server
Built by StackOne StackOne

Coverage

74 Agent Actions

Create, read, update, and delete across Sentry — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Sentry MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Sentry tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Sentry call.

Tools Discovery →

What is the Sentry MCP Server?

A Sentry MCP server lets AI agents read and write Sentry data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Sentry MCP server ships with 74 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Sentry MCP Tools and Actions

Every action from Sentry's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

An Organization Members

  • Retrieve An Organization Member

    Retrieve an organization member's details.

  • Delete An Organization Member

    Remove an organization member.

A Teams

  • Retrieve A Team

    Return details on an individual team.

  • Update A Team

    Update various attributes and configurable settings for the given team.

  • Delete A Team

    Schedules a team for deletion.

A Projects

  • Retrieve A Project

    Return details on an individual project.

  • Delete A Project

    Schedules a project for deletion.

Ownership Configuration For A Projects

  • Retrieve Ownership Configuration For A Project

    Returns details on a project's ownership configuration.

  • Update Ownership Configuration For A Project

    Updates ownership configurations for a project.

An Organization's Releases

  • List An Organization's Releases

    Return a list of releases for a given organization.

  • Retrieve An Organization's Release

    Return details on an individual release.

A Replay Instances

  • Retrieve A Replay Instance

    Return details on an individual replay.

  • Delete A Replay Instance

    Delete a replay.

An Issues

  • Retrieve An Issue

    Return details on an individual issue.

  • Update An Issue

    Updates an individual issue's attributes.

  • Remove An Issue

    Removes an individual issue.

Other (58)

  • Add A Member To An Organization

    Add or invite a member to an organization.

  • Add An Organization Member To A Team

    Add an organization member to a team.

  • Create A New Team

    Create a new team bound to an organization.

  • Add A Team To A Project

    Give a team access to a project.

  • Create A New Project

    Create a new project bound to a team.

  • List Your Organizations

    Return a list of organizations available to the authenticated session.

  • Retrieve An Organization

    Return details on an individual organization, including various details such as membership access and teams.

  • List An Organization's Repositories

    Return a list of version control repositories for a given organization.

  • List An Organization's Projects

    Return a list of projects bound to a organization.

  • List A Repository's Commits

    List commits for a specific repository.

  • List An Organization's Members

    List all organization members.

  • Retrieve An Organization's Events Count By Project

    Query summarized event counts by project for your Organization.

  • Retrieve Event Counts For An Organization (v2)

    Query event counts for your Organization with advanced grouping and filtering.

  • List An Organization's Teams

    Returns a list of teams bound to an organization.

  • List A User's Teams For An Organization

    Returns a list of teams the user has access to in the specified organization.

  • List A Team's Projects

    Return a list of projects bound to a team.

  • List A Team's Members

    List all members on a team.

  • List A Project's Teams

    Return a list of teams that have access to this project.

  • List A Project's Data Filters

    Retrieve a list of filters for a given project.

  • List A Project's Organization Members

    Returns a list of active organization members that belong to any team assigned to the project.

  • List A Project's Users

    Return a list of users seen within this project.

  • List A Tag's Values

    Return a list of values associated with this key.

  • Retrieve Event Counts For A Project

    Return a set of points representing a normalized timestamp and the number of events seen in the period.

  • List A Project's Client Keys

    Return a list of client keys bound to a project.

  • List A Project Release's Commits

    List a project release's commits.

  • List A Project's Release Files

    Return a list of files for a given release.

  • List A Release's Deploys

    Returns a list of deploys based on the organization, version, and project.

  • List An Organization Release's Commits

    List an organization release's commits.

  • List An Organization's Release Files

    Return a list of files for a given release.

  • Retrieve A Project Release's File

    Retrieve a file for a given release.

  • Retrieve An Organization Release's File

    Retrieve a file for a given release.

  • Retrieve Files Changed In A Release's Commits

    Retrieve files changed in a release's commits.

  • Retrieve Statuses Of Release Thresholds (Alpha)

    List all derived statuses of releases that fall within the provided start/end datetimes.

  • List An Organization's Replays

    Return a list of replays belonging to an organization.

  • List An Organization's Selectors

    Return a list of selectors for a given organization.

  • List Recording Segments

    Return a collection of replay recording segments.

  • Retrieve A Recording Segment

    Return a replay recording segment.

  • List Users Who Have Viewed A Replay

    Return a list of users who have viewed a replay.

  • List A Project's Error Events

    Return a list of events bound to a project.

  • List A Project's Issues

    Return a list of issues (groups) bound to a project.

  • List A Tag's Values For An Issue

    Returns a list of values associated with this key for an issue.

  • List An Issue's Events

    Return a list of error events bound to an issue.

  • List An Issue's Hashes

    This endpoint lists an issue's hashes, which are the generated checksums used to aggregate individual events.

  • List An Organization's Issues

    Return a list of issues for an organization.

  • Retrieve An Event For A Project

    Return details on an individual event.

  • Retrieve An Issue Event

    Retrieves the details of an issue event.

  • Retrieve Tag Details

    Return a list of values associated with this key for an issue.

  • Update Organization

    Update settings and properties of an organization.

  • Update Organization Member Roles

    Update a member's organization-level and team-level roles.

  • Update An Organization Member's Team Role

    Update an organization member's team-level role.

  • Delete An Organization Member From A Team

    Delete an organization member from a team.

  • Delete A Team From A Project

    Revoke a team's access to a project.

  • Resolve A Short ID

    Resolve a short ID to the project slug and group details.

  • Resolve An Event ID

    Resolve an event ID to the project slug and internal issue ID and internal event ID.

  • Bulk Mutate A List Of Issues

    Bulk mutate various attributes on issues.

  • Bulk Mutate An Organization's Issues

    Bulk mutate various attributes on a maximum of 1000 issues.

  • Bulk Remove A List Of Issues

    Permanently remove the given issues.

  • Bulk Remove An Organization's Issues

    Permanently remove the given issues.

Set Up Your Sentry MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Sentry in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

More Developer Tools MCP Servers

Azure DevOps

172+ actions

Cloudflare

137+ actions

Bitbucket

134+ actions

Supabase

128+ actions

GitLab

125+ actions

Terraform

118+ actions

OneLogin

109+ actions

Sentry MCP Server FAQ

Sentry MCP server vs direct API integration — what's the difference?
A Sentry MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Sentry. A Sentry MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Sentry at runtime. StackOne provides both.
How does Sentry authentication work for AI agents?
Sentry authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Sentry account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Sentry MCP tools vulnerable to prompt injection?
Yes — Sentry MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Sentry agent and how do I avoid it?
Context bloat happens when Sentry tool schemas and API responses eat your Sentry agent's memory, preventing it from reasoning effectively. A single Sentry query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Sentry agent can access?
Yes — you can limit which actions your Sentry agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Sentry MCP server?
Yes — you can create custom agent actions for your Sentry MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Sentry's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Sentry MCP server?
Skip a Sentry MCP server if your integration is purely software-to-software — direct Sentry API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Sentry actions at runtime.
What AI frameworks and AI clients does the StackOne Sentry MCP server support?
The StackOne Sentry MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.