BugTape demo
Server Details
Read-only sample shop with captured bug evidence. No account or key needed.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
The get_bug_* family (details, events, history, occurrences, users) targets distinct facets of a bug, and the list_* tools are separated by explicit guidance (list_recommended_critical 'instead of list_bugs', list_bug_groups 'prefer over list_bugs'). There is still residual overlap among list_bugs, list_bug_groups, and list_recommended_critical, plus get_bug_occurrences vs get_live_occurrences, but the descriptions largely steer selection correctly.
All 14 tools follow a clean snake_case verb_noun pattern with consistent prefixes (get_bug_*, get_*, list_*). No camelCase or mixed verb styles, and the get_bug_* sub-family is predictable.
14 tools sit comfortably in the well-scoped 3-15 range for a bug triage/investigation server. Each tool covers a distinct resource or view (details, events, users, groups, stats, repro, similarity) without padding.
The surface is thorough on read/investigation but has no write or lifecycle operations: no update status/severity, assign, merge, comment, or acknowledge. Critically, list_bug_groups' description tells the agent to 'Pass both projectId and groupKey as one groupRefs entry to bulk_update_bugs,' yet bulk_update_bugs is not among the tools, leaving a dead-end reference for the triage workflow.
Available Tools
14 toolsget_bugRead an issueARead-onlyIdempotentInspect
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. isExample: true marks BugTape's practice bug (see exampleNote).
Inputs: bugId (required).
get_bug_eventsRead captured eventsARead-onlyIdempotentInspect
Get session events for a bug (DOM, network, console, clicks, errors). Prefer passing occurrenceId so events are not mixed across captures.
Inputs: bugId (required), type, limit, offset, +1 more.
get_bug_historyGet Bug HistoryARead-onlyIdempotentInspect
Get the full audit trail of status/severity changes and assignments on a bug, including who changed what and when.
Inputs: bugId (required).
get_bug_occurrencesGet Bug OccurrencesARead-onlyIdempotentInspect
List the individual occurrences grouped under a bug. Use this to see which users, sessions, releases, or environments were affected.
Inputs: bugId (required), limit, offset.
get_bug_usersGet Bug UsersARead-onlyIdempotentInspect
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.
Inputs: bugId (required), limit, offset.
get_current_orgCurrent workspaceARead-onlyIdempotentInspect
Return the credential workspace. Agent PATs resolve only their own workspace; human sessions use BUGTAPE_ORG_ID.
Inputs: no named parameters.
get_live_occurrencesGet Live OccurrencesARead-onlyIdempotentInspect
Get the most recent occurrences across the organization. Useful for live monitoring and tester workflows. Honors deliveryFeed (tool arg, else PAT / project).
Inputs: limit, deliveryFeed.
get_project_statsGet Project StatsARead-onlyIdempotentInspect
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.
Inputs: projectId (required), days, deliveryFeed.
get_repro_contextRead issue evidenceARead-onlyIdempotentInspect
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. For an example bug (isExample: true) the pack is practice data and costs no credits.
Inputs: bugId (required), eventLimit, occurrenceId.
get_similar_bugsGet Similar BugsARead-onlyIdempotentInspect
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.
Inputs: bugId (required).
list_bug_groupsList Bug GroupsARead-onlyIdempotentInspect
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.
Inputs: sort, limit, offset, search, +8 more.
list_bugsList BugsARead-onlyIdempotentInspect
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. A new project holds one labelled example bug (isExample: true, title starts "Example: "); it is practice data, not from the app.
Inputs: limit, offset, search, status, +4 more.
list_projectsList projectsARead-onlyIdempotentInspect
List all projects in the organization with their bug counts.
Inputs: no named parameters.
list_recommended_criticalFind urgent issuesARead-onlyIdempotentInspect
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.
Inputs: limit, since, projectId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Public read-only catalog and knowledge of the Good Nature Vibe shop. No login.
Custom metal-print storefront: catalog search, product details, shipping, reviews. Read-only.
Demo AI-first shop: search products, fill a cart and prepare the order (test payments).
Read-only product discovery, merchant trust, shipping and returns for SVV-Schatzoekers.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query a Shopify store's orders, products, and inventory levels read-only through the Admin GraphQL API, with no write capability and demo fixtures by default. Runs out of the box without credentials and paces calls on query cost.79 npmMIT
- AlicenseAqualityBmaintenanceEnables reading any public Shopify storefront's product catalogue with variants, SKUs, and prices, plus its collections, through two read-only MCP tools without needing an app or merchant token.270 npm5MIT
- AlicenseBqualityCmaintenanceA read-only MCP server that lets an Agent Studio agent query a WooCommerce store's orders, products, inventory and customers, with pagination, filtering, typed errors and automatic rate-limit retry. It never mutates store data, keeping the blast radius of an agent's actions bounded to reads.7MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to act as a Shopify shopping assistant and catalog auditor by answering from the live storefront: filtered product search, deals, comparisons, recommendations, policy and page lookups, verified cart permalinks, and a whole-catalog listing-quality audit. All operations are read-only, so nothing is ever written to the store.13MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.