bugAgent

-

File and classify bugs— Ask to "File a bug: Login button is unresponsive" andcreate_bug_reportauto-classifies it across 19 types with severity and priority.

Query and filter reports— Uselist_bug_reportsto find bugs by project, severity, status, or type, with server-side filtering before pagination.

Manage the triage queue— Callpick_next_bugto get the next priority bug (S1→S3), thenclaim_bugto atomically assign it to yourself.

Update and comment on tickets— Useupdate_bug_reportto change status or severity, andadd_commentto push notes to linked Jira issues.

Run security and performance tests— Triggerrun_security_scanorrun_performance_test, then

Connect bugAgentto any MCP-compatible AI client.

File, classify, and manage bugs, feature requests, and more directly from your AI coding assistant. No context switching, no copy-paste — just describe the issue and bugAgenthandles the rest.

bugAgentruns the hosted MCP server so AI clients can create, query, and manage bug reports, feature requests, enhancements, and more through theModel Context Protocol. Clients connect directly to the hosted Streamable HTTP endpoint.

Create a Free account; new workspace owners are taken directly to API-key setup. Returning users can generate a key fromSettings → Developers → API Keys.

# Create a bug report "File a bug: Login button is unresponsive on iOS Safari. Steps: tap login, nothing happens. Expected: navigate to dashboard. Severity: high." # bugAgent auto-classifies as UI bug, severity high # File a feature request "Feature request: Add dark mode toggle to the settings page. Users have asked for this in surveys." # Auto-classified as feature-request, severity medium

{ "mcpServers": { "bugagent": { "type": "http", "url": "https://mcp.bugagent.com/mcp", "headers": { "Authorization": "Bearer ba_live_YOUR_KEY_HERE" } } } }

Replaceba_live_YOUR_KEY_HEREwith your actual API key fromSettings → Developers.

{ "mcpServers": { "bugagent": { "command": "npx", "args": ["-y", "bugagent-mcp"], "env": { "BUGAGENT_API_KEY": "ba_live_YOUR_KEY_HERE" } } } }

The bugAgentMCP server is live athttps://mcp.bugagent.com/mcpover Streamable HTTP transport. Connect from any of the eight clients below — pick the one that fits your workflow.

For a small copy-ready configuration, scoped-key guidance, and safe starter prompts, use the publicMCP quickstart.

Prerequisites: Node.js 18 or later. Install fromnodejs.orgif you don’t have it.

{ "mcpServers": { "bugagent": { "type": "http", "url": "https://mcp.bugagent.com/mcp", "headers": { "Authorization": "Bearer ba_live_YOUR_KEY_HERE" } } } }

claude mcp add --transport http bugagent https://mcp.bugagent.com/mcp \ --header "Authorization: Bearer ba_live_YOUR_KEY_HERE"

If you use theOpenAI Codex CLI, export your API key and add bugAgentto~/.codex/config.toml.

[mcp_servers.bugagent] url = "https://mcp.bugagent.com/mcp" bearer_token_env_var = "BUGAGENT_API_KEY"

export BUGAGENT_API_KEY="ba_live_YOUR_KEY_HERE"

Start or restart Codex from that environment. Codex resolves tool calls automatically from your natural-language prompt. Try:“List my open bugs sorted by severity.”

Cursor has built-in MCP support. Add bugAgentonce and the AI assistant inside Cursor can file bugs, list reports, run scans, etc. without leaving your editor.
- Open Cursor →Settings(Cmd+, on Mac / Ctrl+, on Windows) →MCPin the left sidebar.
- Click+ Add new MCP server.
- SelectHTTPtransport type.
- Fill in:

- Name:bugagent

- URL:https://mcp.bugagent.com/mcp
- Header name:Authorization
- Header value:Bearer ba_live_YOUR_KEY_HERE

Alternative: Cursor also reads~/.cursor/mcp.json(Mac) or%USERPROFILE%\.cursor\mcp.json(Windows). Add the same JSON format shown in the Claude Desktop section.

Option 6 — VS Code with Continue extension (Mac + Windows)

If you prefer VS Code, theContinue extensionsupports MCP servers natively.
- Install theContinueextension from the VS Code marketplace.
- Open Continue’s config: Command Palette (Cmd+Shift+P / Ctrl+Shift+P) →Continue: Open config.json. The file is at:

{ "mcpServers": [ { "name": "bugagent", "type": "streamable-http", "url": "https://mcp.bugagent.com/mcp", "requestOptions": { "headers": { "Authorization": "Bearer ba_live_YOUR_KEY_HERE" } } } ] }

Other VS Code MCP-capable extensions: Cline, Roo Code, and Windsurf (fork) all follow similar JSON config patterns with anmcpServerskey and HTTP transport.

Option 7 — OAuth-aware hosts (Claude.ai web shown as the example)

Some MCP hosts authenticate via OAuth 2.0 and ask for a staticclient_idandclient_secretupfront instead of accepting a bearer API key. For those hosts you generate a workspace-scoped OAuth credential pair from the bugAgentdashboard and paste it into the host’s connector form. The credentials are MCP-host-agnostic — any OAuth client supporting Authorization Code + PKCE can use them. The walkthrough below uses the Claude.ai web app as the most common example.
- In bugAgent: openSettings → Developers → MCP Connectors. ClickGenerate connector, give it a name describing the host (e.g.“Claude.ai (work)”), paste the redirect URI your MCP host requires (for the Claude.ai web app that’shttps://claude.ai/api/mcp/auth_callback— check your host’s connector docs for others), and chooseConfidentialfor the auth method. Copy theclient_idandclient_secretshown once on the success screen.
- In your MCP host’s connector / OAuth settings, paste:

- Server URL:https://mcp.bugagent.com/mcp

- Client ID + Client Secret: from step 1
- Authorization URL:https://mcp.bugagent.com/authorize
- Token URL:https://mcp.bugagent.com/tokenFor Claude.ai specifically: go toclaude.ai/customize/connectorsand clickAdd MCP connector.

# Set your API key as a variable export BUGAGENT_API_KEY="ba_live_YOUR_KEY_HERE" # 1. List all available tools curl -N -s https://mcp.bugagent.com/mcp \ -H "Authorization: Bearer $BUGAGENT_API_KEY" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' # 2. Call a tool — list 5 reports from a specific project curl -N -s https://mcp.bugagent.com/mcp \ -H "Authorization: Bearer $BUGAGENT_API_KEY" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{ "jsonrpc":"2.0", "id":2, "method":"tools/call", "params":{ "name":"list_bug_reports", "arguments":{"project":"bugagent","limit":5} } }'

# Set your API key $env:BUGAGENT_API_KEY = "ba_live_YOUR_KEY_HERE" # Use Invoke-RestMethod (PowerShell's curl equivalent) $headers = @{ "Authorization" = "Bearer $env:BUGAGENT_API_KEY" "Content-Type" = "application/json" "Accept" = "application/json, text/event-stream" } # 1. List all tools $body = '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' Invoke-RestMethod -Uri "https://mcp.bugagent.com/mcp" \ -Method Post -Headers $headers -Body $body # 2. Call list_bug_reports for a specific project $body = @{ jsonrpc = "2.0" id = 2 method = "tools/call" params = @{ name = "list_bug_reports" arguments = @{ project = "bugagent"; limit = 5 } } } | ConvertTo-Json -Depth 5 Invoke-RestMethod -Uri "https://mcp.bugagent.com/mcp" \ -Method Post -Headers $headers -Body $body

Troubleshooting 401 Unauthorized:Check that your API key hasn’t been revoked inSettings → Developers. Keys start withba_live_. If you’re still stuck, regenerate the key and retry.

List my 5 most recent bug reports Show all open critical bugs in the Auth project Create a bug titled "Login broken on Safari" with severity s2 Update TEST-451 status to in-progress and assign it to me Add a comment to TEST-451: "root cause confirmed — null check missing in auth middleware" Show me everything filed this week, grouped by severity

Create a test suite called "Smoke Tests" with cases for login, checkout, and account settings Run the Regression suite and list all failures Use Hermes to execute the curated "Checkout smoke" suite and report every result to bugAgent Show failing test cases from the last 7 days Which test cases have never been run in the past 90 days? Get a pass-rate trend for this month vs last month

Run a security scan on https://app.example.com Get this month's security scan results — show only high and critical findings Create a performance test for the landing page and check Lighthouse scores What are the Core Web Vitals for our checkout flow?

Create a Playwright script that logs in and verifies the dashboard loads Run the checkout automation on iPhone 15 Pro on a real device Optimize the login automation script Show runs for the checkout automation — any failures? Schedule the smoke test suite to run every weekday at 6 AM UTC

Run an exploratory AI session on https://app.example.com with 5 parallel agents Get the latest exploration run results — list any bugs that were filed What testing strategies did the agents use and which found the most issues?

Check my plan usage for this month Show team bug stats for this week broken down by severity and type List all team members and their roles How many security scans do I have left this month?

401 UnauthorizedKey is wrong, expired, or revoked. CheckSettings → Developers— keys start withba_live_. Regenerate if needed.

Wrong workspace’s data Each API key is scoped to one workspace. Generate a new key from the workspace you want to query inSettings → Developers.

Codex CLI — tools not recognized Verify~/.codex/config.tomluses[mcp_servers.bugagent], setbearer_token_env_var = "BUGAGENT_API_KEY", and export that variable before starting Codex. Checkcodex --versionif tools still do not appear.

The bugAgentMCP server provides tools for:

- create_bug_report— File a new report with auto-classification across 19 types — bugs, feature requests, enhancements, technical debt, and more (title: 3-500 chars). Optionalattachmentsarray accepts base64-encoded files up to 400 MB each: any image, video, audio, PDF, or text/JSON. Setformat_description: trueto auto-reformat the description into a structured template using AI. Passtime_spent_secondsto track QA effort. Passpriority(urgent/high/normal/low) to set the fix urgency independently of severity. Passis_epic: trueto create an Epic, orparent_epic_id(UUID/short ID) to create a child in the same authorized project. The response includes hierarchy fields plusproject_id,project,short_id,legacy_short_id, andproject_short_id.
- list_bug_reports— List and filter reports (max 100 per page). Project filters are applied server-side before pagination. Filter byproject(UUID, slug, exact name, or ticket prefix),project_id,project_slug,project_prefix,workspace(UUID, exact name, or workspace ticket prefix),workspace_id/team_id,is_epic,type,severity,status,resolution,root_cause, orreporter_user_id. Each result includes tenant-scoped people/project identifiers plusis_epic,parent_epic_id,parent_epic, and boundedepic_progress. Report-read tools do not expose member email addresses.
- pick_next_bug— Returns the next bug(s) the agent loop should work on, in priority order (S1 → S2 → S3, oldest first within each bucket). Automatically scoped to your workspace — returns tickets across all projects in your team withstatusnew,awaiting-triage, orconfirmedand severity S1-S3.Read-only— does not atomically claim tickets. Optionalseverity(single tier),limit(1-50, default 1). Returns rows in the same shape aslist_bug_reportsfor tool composability. Pair withclaim_bugfor the read-then-claim pattern.
- claim_bug— Atomically transition a bug fromstatusnew,awaiting-triage, orconfirmedtostatus='in-progress', setassigned_toto the calling user, and stampclaimed_at=NOW(). Race-free across concurrent callers via Postgres' UPDATE-WHERE-RETURNING pattern — if two agents callclaim_bugon the same id in close succession, exactly one getsclaimed:truewith the bug body and the other getsclaimed:falsewith a reason string. Successful responses includereporter_user_id,reporter_name,assigned_to, andassignee_name. A pg_cron reaper releases stale claims (status=in-progress+claimed_at> 30 minutes old) back tonewautomatically, so a crashed agent's tickets re-enter the queue without manual intervention. Inputs:id(UUID or short ID).
- get_bug_report— Get full details of a report by UUID or workspace/project short ID. Returns the standard people/project/quality fields plusis_epic, parent identity, aggregate progress, and a bounded first child page for Epics.
- list_epic_children— Paginate an Epic's child reports withid,limit(1–100), andoffset. Returnschildren,total,has_more, and SQL-aggregatedepic_progresswithout loading every child report.
- update_bug_report— Update standard report fields plusis_epicandparent_epic_id. Passparent_epic_id: nullto detach; reparent/detach is atomic and requires same-workspace, same-project authorization. Promoting to an Epic detaches an existing parent, while an Epic with children cannot be demoted. Existing status/resolution/root-cause and assignment notification rules still apply.
- add_comment— Add a comment to a bug report (UUID or short ID, body 1-10000 chars). If the report is synced to Jira, the comment is automatically pushed to the linked Jira issue.
- list_comments— List a report's full comment thread, oldest first — each comment with author name,parentId(threaded replies), and timestamps. Comments are not part ofget_bug_report, so this is how you read a ticket's discussion. Accepts UUID or short ID.
- link_bug_reports— Create a directional semantic link between two reports in the same authorized project. Forparent-of, the from-report must be an Epic and the to-report a standard child. Preferparent_epic_idon create/update for Epic assignment.
- unlink_bug_reports— Remove a previously-created bug-report link by its UUID (link_id, returned bylink_bug_reportsorlist_bug_report_links).
- list_bug_report_links— List every user-curated link touching a bug report. Returns each link as it reads from the supplied report's perspective — e.g. a storedduplicate-ofrow where this report is the target renders asduplicated-by;parent-ofwhere this report is the target renders assubtask-of;depends-onwhere this report is the target renders asblocks;testing-blocked-bywhere this report is the target renders asblocks-testing.related-tois symmetric. Complements the auto-detectedsimilar_reportsfield returned byget_bug_report.
- classify_bug— Classify a description into one of 19 report types (bugs, features, enhancements, etc.) with confidence score
- flush_reports— Bulk delete old reports (admin only)

- get_usage— Check usage against plan limits. API-key callers requireusage:read.
- get_stats— Daily counts, type/severity/status breakdowns

- list_projects— List available projects withid,name,slug,ticket_prefix, description, and default status. Use those values withcreate_bug_reportandlist_bug_reportsto target the correct project.
- create_project— Create a new project (auto-becomes default if first)
- delete_project— Permanently delete a project and all associated data (bug reports, automations, test cases, mobile apps, schedules, geo snaps, notes, time entries). Only owner/manager. Cannot delete last project. Storage is freed automatically
- export_okf_bundle— Export a project’s QA knowledge — bug reports, test cases, automations, and performance, security, and exploratory tests — as an OKF/OQA markdown bundle (the Open Query Agent format used byoqa.ai). Defaults to the active project; pass the optionalproject(slug or name) to export a different one. Returns the list of files in the bundle plus the bundle itself as a base64-encoded zip