BugTape demo

Read-only sample shop with captured bug evidence. No account or key needed.

我该使用它吗

质量与安全性

A
描述质量
95%
模式完整度
86%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

发现(1)

  • LOWTool 'get_current_org' description lacks action verb在 get_current_org 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~3,009token 数(工具定义)
~1.5 KB典型响应大小
对注意力有显著影响(占 128k 上下文窗口的 2.35%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "bugtape-demo": {
      "url": "https://app.bugtape.ai/demo/mcp"
    }
  }
}

远程端点

https://app.bugtape.ai/demo/mcpstreamable-http

它能做什么

工具清单

工具(14)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢list_bugs(status, severity, projectId, platform, deliveryFeed, ...)

List bugs for the organization (flat, one row per deduplicated report). Supports filtering by status, severity, project, platform, deliveryFeed (all | urgent_critical | ui_ux), and text search. Each row includes affected_user_count, repeat_user_count, and user_spread (user_specific vs widespread). Diagnostic-class signals are excluded by default. Prefer list_bug_groups for grouped triage.

输入模式

{
  "type": "object",
  "properties": {
    "status": {
      "type": "string",
      "enum": [
        "new",
        "known",
        "working",
        "resolved",
        "silenced",
        "awaiting_verification",
        "verified_fixed"
      ],
      "description": "Filter by bug status"
    },
    "severity": {
      "type": "string",
      "enum": [
        "critical",
        "high",
        "medium",
        "low"
      ],
      "description": "Filter by severity"
    },
    "projectId": {
      "type": "string",
      "format": "uuid",
      "description": "Filter by project ID"
    },
    "platform": {
      "type": "string",
      "enum": [
        "web",
        "ios",
        "android",
        "react-native",
        "flutter",
        "server",
        "other"
      ],
      "description": "Only bugs with an occurrence captured on this platform"
    },
    "deliveryFeed": {
      "type": "string",
      "enum": [
        "all",
        "urgent_critical",
        "ui_ux"
      ],
      "description": "Delivery feed: all, urgent_critical (severity Score ≥ high and confidence ≥ 0.80), or ui_ux (is_ui_ux Noul ≥ 0.70). Defaults to the PAT or project setting."
    },
    "search": {
      "type": "string",
      "description": "Search text in title and description"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 200,
      "default": 20,
      "description": "Number of results (default 20)"
    },
    "offset": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Pagination offset"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_bug(bugId)

Get full details of a bug including title, description, severity, status, reporters, AI summary, environment info, report count, affected_user_count, repeat_user_count, and user_spread (user_specific vs widespread). Use get_bug_users for the per-user roster.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The bug ID"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_bug_events(bugId, occurrenceId, type, limit, offset)

Get session events for a bug (DOM, network, console, clicks, errors). Prefer passing occurrenceId so events are not mixed across captures.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The bug ID"
    },
    "occurrenceId": {
      "type": "string",
      "format": "uuid",
      "description": "Pin events to one occurrence (recommended)"
    },
    "type": {
      "type": "string",
      "description": "Filter by event type (e.g., \"click\", \"console-error\", \"network\")"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 1000,
      "default": 100,
      "description": "Max events to return"
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991,
      "default": 0,
      "description": "Continue from the previous response nextOffset"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_repro_context(bugId, occurrenceId, eventLimit)

Build an agent-consumable reproduction pack: evidence (timeline, status, env) separate from inference (AI summary). Prefer occurrenceId so sessions are not interleaved. Not raw rrweb. Same pack as resources/read bugtape://bugs/{bugId}/repro.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The bug ID"
    },
    "occurrenceId": {
      "type": "string",
      "format": "uuid",
      "description": "Pin to one occurrence. If omitted, uses the latest occurrence when available."
    },
    "eventLimit": {
      "type": "number",
      "minimum": 20,
      "maximum": 500,
      "default": 200,
      "description": "Max raw events to scan before summarizing"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_projects

List all projects in the organization with their bug counts.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_project_stats(projectId, days, deliveryFeed)

Get aggregate statistics for a project (server-computed over bugs in the elected delivery feed, not a sample): counts by status and severity, daily timeline, top unresolved bugs by report count, MTTR, health score, and previous-period comparison.

输入模式

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "format": "uuid",
      "description": "Project ID"
    },
    "days": {
      "type": "number",
      "minimum": 1,
      "maximum": 365,
      "default": 30,
      "description": "Timeline window in days (default 30)"
    },
    "deliveryFeed": {
      "type": "string",
      "enum": [
        "all",
        "urgent_critical",
        "ui_ux"
      ],
      "description": "Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting."
    }
  },
  "required": [
    "projectId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_bug_occurrences(bugId, limit, offset)

List the individual occurrences grouped under a bug. Use this to see which users, sessions, releases, or environments were affected.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The grouped bug ID"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 200,
      "default": 50,
      "description": "Max occurrences to return"
    },
    "offset": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Pagination offset"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_bug_users(bugId, limit, offset)

Who hit this bug: one row per affected end user (the app's identify() userId, else reporter email, else an anonymous IP-hash key) with firstSeen, lastSeen, occurrenceCount, platforms (web/ios/…), lastRelease and lastOccurrenceId. Pass a row's userKey to get_user_timeline to see everything that user experienced across bugs, or to get_repro_context via occurrenceId=lastOccurrenceId.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The grouped bug ID"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 200,
      "default": 50,
      "description": "Max users to return (newest last-seen first)"
    },
    "offset": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Pagination offset"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_live_occurrences(limit, deliveryFeed)

Get the most recent occurrences across the organization. Useful for live monitoring and tester workflows. Honors deliveryFeed (tool arg, else PAT / project).

输入模式

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 200,
      "default": 50,
      "description": "Max live occurrences to return"
    },
    "deliveryFeed": {
      "type": "string",
      "enum": [
        "all",
        "urgent_critical",
        "ui_ux"
      ],
      "description": "Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_current_org

Return the credential workspace. Agent PATs resolve only their own workspace; human sessions use BUGTAPE_ORG_ID.

输入模式

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_bug_history(bugId)

Get the full audit trail of status/severity changes and assignments on a bug, including who changed what and when.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The bug ID"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_similar_bugs(bugId)

Find other bugs similar to the given bug, ranked by similarity score (0-100, fingerprint + title overlap). Returns up to 5 matches. Useful before merging or triaging.

输入模式

{
  "type": "object",
  "properties": {
    "bugId": {
      "type": "string",
      "format": "uuid",
      "description": "The bug ID to find similar bugs for"
    }
  },
  "required": [
    "bugId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_bug_groups(projectId, platform, assignee, status, severity, ...)

Grouped triage view: bugs collapsed across pages by error signature (one group per distinct error within a project, even when dedup created many bug rows). Each group includes projectId + groupKey (the stable group identity), a representative sampleBugId/sampleTitle, instanceCount, occurrenceCount, sessionCount, userCount, maxSeverity, topStatus, signalReason (why the classifier flagged it), browsers/oses, platforms (web/ios/android/react-native/flutter/server — one issue can span several), and anyRegression. Pass both projectId and groupKey as one groupRefs entry to bulk_update_bugs. Legacy groupKeys are accepted only when unique across the organization and are rejected when ambiguous. Prefer this over list_bugs for triage.

输入模式

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "format": "uuid",
      "description": "Filter by project ID"
    },
    "platform": {
      "type": "string",
      "enum": [
        "web",
        "ios",
        "android",
        "react-native",
        "flutter",
        "server",
        "other"
      ],
      "description": "Only groups with an occurrence captured on this platform"
    },
    "assignee": {
      "type": "string",
      "description": "'unassigned', or a user id from list_team — narrows to bugs assigned to that person (or none)"
    },
    "status": {
      "type": "string",
      "enum": [
        "new",
        "known",
        "working",
        "resolved",
        "silenced",
        "awaiting_verification",
        "verified_fixed"
      ],
      "description": "Filter by per-bug status (groups also expose aggregated topStatus)"
    },
    "severity": {
      "type": "string",
      "enum": [
        "critical",
        "high",
        "medium",
        "low"
      ],
      "description": "Filter by per-bug severity"
    },
    "search": {
      "type": "string",
      "description": "Search text in title and description"
    },
    "deliveryFeed": {
      "type": "string",
      "enum": [
        "all",
        "urgent_critical",
        "ui_ux"
      ],
      "description": "Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting."
    },
    "unresolved": {
      "type": "boolean",
      "default": false,
      "description": "true = only groups whose aggregated topStatus is not resolved/silenced"
    },
    "sort": {
      "type": "string",
      "enum": [
        "last_seen",
        "first_seen",
        "count",
        "severity",
        "title",
        "signal",
        "assignee"
      ],
      "default": "last_seen",
      "description": "Sort key: last_seen (default), first_seen, count (occurrences), severity, title, signal (regressions first), assignee (display name, unassigned last)"
    },
    "direction": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ],
      "default": "desc",
      "description": "Sort direction for the chosen key (default desc; ties break on last_seen desc)"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 200,
      "default": 20,
      "description": "Number of groups (default 20)"
    },
    "offset": {
      "type": "number",
      "minimum": 0,
      "default": 0,
      "description": "Pagination offset"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_recommended_critical(projectId, limit, since)

Start here. Returns `sentToYou` first: bugs a person sent you with "Send to agent" (fix these first), then the prefiltered agent inbox: one row per signature group, new unique issues scored critical/high (or regressions). `id` is the best qualifying member. `member_id_sample` is at most 8 member ids; `instance_count` is the full count and `instances_path` lists the rest. Use this instead of list_bugs for what to work on. Diagnostic, silenced, and agent-acked rows are excluded.

输入模式

{
  "type": "object",
  "properties": {
    "projectId": {
      "type": "string",
      "format": "uuid"
    },
    "limit": {
      "type": "number",
      "minimum": 1,
      "maximum": 100,
      "default": 20
    },
    "since": {
      "type": "string",
      "description": "ISO timestamp; only rows recommended after this"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本14 个工具