Loading ToolBench

Reading the current corpus…

selfhosted-sentry-mcp MCP server · D · ToolBench

← Browse

selfhosted-sentry-mcp

github.com/houfeng0923/selfhosted-sentry-mcp

Model context protocol server for self hosted sentry instances, 支持自动读取 ~/.sentryclirc 配置。

2026-07-28+STDIO6 tools

56/100

Definition Quality75

Protocol Readiness50

Supportability28

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Summary

Server has 6 tools with complete input schemas and descriptions. Naming follows verb_noun convention (get_, list_, update_, create_). Descriptions are present but brief (avg 80 chars, below 194-char baseline). All parameters have type definitions and descriptions. However, output schemas are not documented, LLMs cannot predict response structure for chaining. Error handling exists but lacks recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Parameter descriptions lack format constraints and validation rules.

Tools (6)

create_sentry_issue_commentwriteauthsource verified73/100

Add a comment to a Sentry issue.

get_sentry_event_detailsread onlyauthsource verified75/100

Retrieve details for a specific event ID within a project.

get_sentry_issueread onlyauthsource verified77/100

Retrieve details for a specific Sentry issue by ID or URL.

list_sentry_issuesread onlyauthsource verified78/100

List issues for a specific project, optionally filtering by query or status.

list_sentry_projectsread onlyauthsource verified72/100

List all projects within the configured Sentry organization.

update_sentry_issue_statuswriteauthsource verified73/100

Update the status of a Sentry issue.

Issues (5)

HIGHtool ↗

Output schemas not documented. LLMs cannot predict response structure, breaking tool chaining and forcing exploratory calls.

get_sentry_issuelist_sentry_projectslist_sentry_issuesget_sentry_event_detailsupdate_sentry_issue_statuscreate_sentry_issue_comment

HIGHtool-description ↗

Descriptions lack actionable context. 'Retrieve details for a specific Sentry issue by ID or URL' does not explain WHEN to use this vs list_sentry_issues, or what fields are returned.

get_sentry_issueget_sentry_event_details

MEDIUMtool ↗

No tool annotations (readOnlyHint, destructiveHint). LLMs cannot distinguish safe read-only tools from destructive ones without explicit hints.

update_sentry_issue_statuscreate_sentry_issue_comment

MEDIUMconstrained-input ↗

Parameter descriptions lack format constraints. 'issue_id_or_url' accepts both formats but does not specify expected format (numeric ID vs full URL pattern).

Recommendations

Document output schemas for all tools. Example: 'Returns {issue_id: string, title: string, status: enum[resolved|unresolved|ignored], created: ISO8601, events_count: number}'. This enables LLMs to chain tools and extract needed fields.
Add tool annotations to ListToolsRequestSchema response. Mark read-only tools with readOnlyHint: true; mark destructive tools (update_*, create_*) with destructiveHint: true. This guides LLM safety reasoning.
Expand descriptions to 100-150 chars with WHEN context. Example: 'Retrieve full details for a Sentry issue by ID or URL. Use this after list_sentry_issues to get stack traces, events, and assignee info. Returns issue_id, title, status, stack_trace, events[].'
Add format constraints to parameter descriptions. Example: 'issue_id_or_url: Numeric issue ID (e.g. 12345) or full Sentry URL (https://sentry.io/organizations/my-org/issues/12345/). Accepts either format.'
Enhance error messages with recovery guidance. Example: Instead of 'Invalid args for get_sentry_issue', return 'Invalid issue_id_or_url. Expected numeric ID (e.g. 12345) or full URL (https://sentry.io/...). Got: {actual_value}. Try list_sentry_issues() first to find valid issue IDs.'

Score history

Overall score trend

First recorded score · v2 rubric

56/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	56	2026-07-28+	v2