Provides tools for retrieving and analyzing error reports from Sentry.io, including the ability to fetch detailed issue information, view stacktraces, and list issues by project to help with debugging and error monitoring.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Sentry show me the latest issues for my-api project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server for retrieving and analyzing issues from Sentry.io. This server provides tools to inspect error reports, stacktraces, and other debugging information from your Sentry account.
get_sentry_issue
Retrieve and analyze a Sentry issue by ID or URL
Input:
issue_id_or_url (string): Sentry issue ID or URL to analyze
Returns: Issue details including:
Title
Issue ID
Status
Level
First seen timestamp
Last seen timestamp
Event count
Full stacktrace
get_list_issues
Retrieve and analyze Sentry issues by project slug
Input:
project_slug (string): Sentry project slug to analyze
organization_slug (string): Sentry organization slug to analyze
Returns: List of issues with details including:
Title
Issue ID
Status
Level
First seen timestamp
Last seen timestamp
Event count
Basic issue information
sentry-issue
Retrieve issue details from Sentry
Input:
issue_id_or_url (string): Sentry issue ID or URL
Returns: Formatted issue details as conversation context
Related MCP server: MCP Server Sentry
To install mcp-sentry for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @qianniuspace/mcp-sentry --client claudeWhen using uv no specific installation is needed. We will
use uvx to directly run mcp-sentry.
Alternatively you can install mcp-sentry via pip:
pip install mcp-sentryor use uv
uv pip install -e .After installation, you can run it as a script using:
python -m mcp_sentryAdd this to your claude_desktop_config.json:
"mcpServers": {
"sentry": {
"command": "uvx",
"args": ["mcp-sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}"mcpServers": {
"sentry": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}"mcpServers": {
"sentry": {
"command": "python",
"args": ["-m", "mcp_sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}Add to your Zed settings.json:
For Example Curson
"context_servers": [
"mcp-sentry": {
"command": {
"path": "uvx",
"args": ["mcp-sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
}
],"context_servers": {
"mcp-sentry": {
"command": "python",
"args": ["-m", "mcp_sentry", "--auth-token", "YOUR_SENTRY_TOKEN","--project-slug" ,"YOUR_PROJECT_SLUG", "--organization-slug","YOUR_ORGANIZATION_SLUG"]
}
},"context_servers": {
"sentry": {
"command": "python",
"args": [
"-m",
"mcp_sentry",
"--auth-token",
"YOUR_SENTRY_TOKEN",
"--project-slug",
"YOUR_PROJECT_SLUG",
"--organization-slug",
"YOUR_ORGANIZATION_SLUG"
],
"env": {
"PYTHONPATH": "path/to/mcp-sentry/src"
}
}
},You can use the MCP inspector to debug the server. For uvx installations:
npx @modelcontextprotocol/inspector uvx mcp-sentry --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUGOr if you've installed the package in a specific directory or are developing on it:
cd path/to/servers/src/sentry
npx @modelcontextprotocol/inspector uv run mcp-sentry --auth-token YOUR_SENTRY_TOKEN --project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG or in term
npx @modelcontextprotocol/inspector uv --directory /Volumes/ExtremeSSD/MCP/mcp-sentry/src run mcp_sentry --auth-token YOUR_SENTRY_TOKEN
--project-slug YOUR_PROJECT_SLUG --organization-slug YOUR_ORGANIZATION_SLUG
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Retrieve and analyze Sentry issues by project slug. Use this tool when you need to: - Investigate production errors and crashes - Access detailed stacktraces from Sentry - Analyze error patterns and frequencies - Get information about when issues first/last occurred - Review error counts and status
| Name | Required | Description | Default |
|---|---|---|---|
| project_slug | No | Sentry project slug to analyze | |
| organization_slug | No | Sentry organization slug to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full disclosure burden. It successfully describes the data accessed (stacktraces, counts, first/last occurrence dates) but omits safety classification (read-only vs. destructive), authentication requirements, or rate limiting constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with the core purpose front-loaded in the first sentence, followed by actionable bullet points. Each of the five use-case bullets earns its place by clarifying distinct capabilities. Slightly verbose but efficiently organized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple 2-parameter schema and lack of output schema, the description adequately compensates by detailing the returned information (stacktraces, status, counts) within the text. Missing only safety/permission context which would normally appear in annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for both 'project_slug' and 'organization_slug', establishing a baseline of 3. The description references 'by project slug' confirming the primary filter, but does not add format constraints, examples, or explain the optional nature of parameters (required: [] in schema).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb-resource combination ('Retrieve and analyze Sentry issues') and scopes it to 'by project slug'. It distinguishes from sibling 'get_sentry_issue' by emphasizing aggregate capabilities like 'patterns and frequencies' and 'error counts' vs. single-issue retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'Use this tool when you need to:' preamble followed by five specific scenarios (investigate crashes, access stacktraces, analyze patterns, etc.) provides excellent contextual guidance. Lacks an explicit pointer to sibling 'get_sentry_issue' for single-issue lookups, preventing a perfect score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve and analyze a Sentry issue by ID or URL. Use this tool when you need to: - Investigate production errors and crashes - Access detailed stacktraces from Sentry - Analyze error patterns and frequencies - Get information about when issues first/last occurred - Review error counts and status
| Name | Required | Description | Default |
|---|---|---|---|
| issue_id_or_url | Yes | Sentry issue ID or URL to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses what data is returned (stacktraces, frequencies, first/last occurrence, status) but omits operational concerns: authentication requirements, rate limits, error handling for invalid IDs, or privacy implications of accessing production errors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with purpose front-loaded in the first sentence, followed by explicit usage guidelines. Bullet points are specific and non-redundant. Slightly verbose compared to minimalist ideal, but every sentence serves distinct selection or invocation guidance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter retrieval tool without output schema, description adequately hints at return value structure by listing accessible data types (stacktraces, error patterns, temporal metadata). Missing only operational edge cases; sufficient for agent to understand tool capabilities and expected output richness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (single parameter 'issue_id_or_url' fully documented). Description mentions 'by ID or URL' which aligns with schema but adds no additional semantic value such as format examples, validation rules, or distinction between ID vs URL input behavior. Baseline 3 appropriate for complete schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Opens with specific verb+noun combination ('Retrieve and analyze a Sentry issue') and clearly identifies the lookup method ('by ID or URL'). Effectively distinguishes from sibling 'get_list_issues' by emphasizing singular issue retrieval versus listing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly prefixes usage scenarios with 'Use this tool when you need to:' followed by five specific bulleted contexts (production errors, stacktraces, error patterns, temporal data, counts/status). Lacks explicit 'when not to use' or named alternative, but sibling tool name provides clear contrast.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.6.2get_list_issuesget_sentry_issueThe two tools are essentially indistinguishable in purpose. Both descriptions are identical, listing the exact same use cases (investigate errors, access stacktraces, analyze patterns, get timing info, review counts). An agent would have no way to determine when to use get_list_issues versus get_sentry_issue since they appear to serve the same function.
Both tools follow a similar get_ prefix pattern, which provides some consistency. However, the naming is confusingly similar (get_list_issues vs get_sentry_issue) rather than clearly differentiated, and the verb-noun structure is mixed (list_issues vs sentry_issue).
With only 2 tools, this feels severely under-scoped for a Sentry integration. A production error monitoring system would typically need tools for creating issues, updating statuses, searching/filtering, accessing events, or managing projects. Two tools is too few to cover meaningful workflows.
The tool surface is severely incomplete for Sentry's domain. There are no tools for creating issues, updating issue status (resolve/ignore), searching across projects, accessing event details, managing alerts, or any administrative functions. The two existing tools appear redundant rather than complementary.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
A Model Context Protocol (MCP) application for automated GitHub PR analysis and issue management.…
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for Studex tools, notifications, and profile integrations
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/MCP-100/mcp-sentry'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
