# BugTape demo (remote · app.bugtape.ai)

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

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `app.bugtape.ai`: 77/100 (this document), [markdown](https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp.md), [page](https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp)

## Channel facts

- Endpoint: `https://app.bugtape.ai/demo/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1847 tokens (~131/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the BugTape demo MCP server?

BugTape demo is a hosted endpoint at https://app.bugtape.ai/demo/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-bugtape-bugtape-demo 'https://app.bugtape.ai/demo/mcp'
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "ai-bugtape-bugtape-demo": {
      "type": "http",
      "url": "https://app.bugtape.ai/demo/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-bugtape-bugtape-demo]
url = "https://app.bugtape.ai/demo/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-bugtape-bugtape-demo": {
      "type": "remote",
      "url": "https://app.bugtape.ai/demo/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-bugtape-bugtape-demo --url 'https://app.bugtape.ai/demo/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-bugtape-bugtape-demo:
    url: "https://app.bugtape.ai/demo/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-bugtape-bugtape-demo": {
      "Transport": "http",
      "Url": "https://app.bugtape.ai/demo/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-bugtape-bugtape-demo -t streamable-http -u 'https://app.bugtape.ai/demo/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-bugtape-bugtape-demo": {
      "type": "http",
      "url": "https://app.bugtape.ai/demo/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 76, +1)

- [security] Tool “get_bug” rewrote its description, which is the text the model reads
- [security] Tool “get_repro_context” rewrote its description, which is the text the model reads
- [security] Tool “list_bugs” rewrote its description, which is the text the model reads

### 2026-10-31 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 73, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-26 (score 73)

First indexed and scored.

## MCP tools (14)

### `list_bugs` (~259 tokens)

List Bugs

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.

Input parameters:

- `deliveryFeed` (string): 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.
- `limit` (number): Number of results (default 20)
- `offset` (number): Pagination offset
- `platform` (string): Only bugs with an occurrence captured on this platform
- `projectId` (string): Filter by project ID
- `search` (string): Search text in title and description
- `severity` (string): Filter by severity
- `status` (string): Filter by bug status

### `get_bug` (~88 tokens)

Read an issue

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).

Input parameters:

- `bugId` (string, required): The bug ID

### `get_bug_events` (~113 tokens)

Read captured events

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

Input parameters:

- `bugId` (string, required): The bug ID
- `limit` (number): Max events to return
- `occurrenceId` (string): Pin events to one occurrence (recommended)
- `offset` (integer): Continue from the previous response nextOffset
- `type` (string): Filter by event type (e.g., "click", "console-error", "network")

### `get_repro_context` (~136 tokens)

Read issue evidence

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.

Input parameters:

- `bugId` (string, required): The bug ID
- `eventLimit` (number): Max raw events to scan before summarizing
- `occurrenceId` (string): Pin to one occurrence. If omitted, uses the latest occurrence when available.

### `list_projects` (~19 tokens)

List projects

List all projects in the organization with their bug counts.

### `get_project_stats` (~112 tokens)

Get Project Stats

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.

Input parameters:

- `days` (number): Timeline window in days (default 30)
- `deliveryFeed` (string): Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting.
- `projectId` (string, required): Project ID

### `get_bug_occurrences` (~67 tokens)

Get Bug Occurrences

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

Input parameters:

- `bugId` (string, required): The grouped bug ID
- `limit` (number): Max occurrences to return
- `offset` (number): Pagination offset

### `get_bug_users` (~138 tokens)

Get Bug Users

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.

Input parameters:

- `bugId` (string, required): The grouped bug ID
- `limit` (number): Max users to return (newest last-seen first)
- `offset` (number): Pagination offset

### `get_live_occurrences` (~80 tokens)

Get Live Occurrences

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

Input parameters:

- `deliveryFeed` (string): Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting.
- `limit` (number): Max live occurrences to return

### `get_current_org` (~33 tokens)

Current workspace

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

### `get_bug_history` (~43 tokens)

Get Bug History

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

Input parameters:

- `bugId` (string, required): The bug ID

### `get_similar_bugs` (~64 tokens)

Get Similar Bugs

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.

Input parameters:

- `bugId` (string, required): The bug ID to find similar bugs for

### `list_bug_groups` (~404 tokens)

List Bug Groups

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.

Input parameters:

- `assignee` (string): 'unassigned', or a user id from list_team — narrows to bugs assigned to that person (or none)
- `deliveryFeed` (string): Delivery feed: all, urgent_critical, or ui_ux. Defaults to the PAT or project setting.
- `direction` (string): Sort direction for the chosen key (default desc; ties break on last_seen desc)
- `limit` (number): Number of groups (default 20)
- `offset` (number): Pagination offset
- `platform` (string): Only groups with an occurrence captured on this platform
- `projectId` (string): Filter by project ID
- `search` (string): Search text in title and description
- `severity` (string): Filter by per-bug severity
- `sort` (string): Sort key: last_seen (default), first_seen, count (occurrences), severity, title, signal (regressions first), assignee (display name, unassigned last)
- `status` (string): Filter by per-bug status (groups also expose aggregated topStatus)
- `unresolved` (boolean): true = only groups whose aggregated topStatus is not resolved/silenced

### `list_recommended_critical` (~157 tokens)

Find urgent issues

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.

Input parameters:

- `limit` (number)
- `projectId` (string)
- `since` (string): ISO timestamp; only rows recommended after this

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp#diagnostics

## Score history

- 2026-11-05: 77
- 2026-11-04: 77
- 2026-11-03: 76
- 2026-11-02: 76
- 2026-11-01: 75
- 2026-10-31: 75
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 74
- 2026-10-27: 73
- 2026-10-26: 73

## Common questions

### What is the BugTape demo MCP server?

BugTape demo is an MCP server listed in the public MCP registry as ai.bugtape/bugtape-demo. Read-only sample shop with captured bug evidence. No account or key needed. This page covers its hosted endpoint (https://app.bugtape.ai/demo/mcp).

### Is the BugTape demo MCP server safe to use?

BugTape demo scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the BugTape demo MCP server expose?

BugTape demo exposes 14 tools: list_bugs, get_bug, get_bug_events, get_repro_context, list_projects, and 9 more. Their descriptions and schemas cost roughly 1,713 tokens of context every time the server is loaded.

### Does the BugTape demo MCP server require authentication?

No. We connected to BugTape demo without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the BugTape demo MCP server still maintained?

BugTape demo is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://app.bugtape.ai/demo/mcp
- Website: https://bugtape.ai/agents/
- Changelog RSS feed: https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-bugtape-bugtape-demo/demo-mcp