Honeybadger

An MCP (Model Context Protocol) server forHoneybadger, providing structured access to Honeybadger's API through the MCP protocol.

docker pull ghcr.io/honeybadger-io/honeybadger-mcp-server:latest

Then, configure your MCP client(s). You can find your personal auth token under the "Authentication" tab in yourHoneybadger user settings.

Put this config in~/.cursor/mcp.jsonforCursor, or~/.codeium/windsurf/mcp_config.jsonforWindsurf. See Anthropic'sMCP quickstart guidefor how to locate yourclaude_desktop_config.jsonfor Claude Desktop:

{ "mcpServers": { "honeybadger": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "HONEYBADGER_PERSONAL_AUTH_TOKEN", "ghcr.io/honeybadger-io/honeybadger-mcp-server" ], "env": { "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token" } } } }

Run this command to configureClaude Code:

claude mcp add honeybadger -- docker run -i --rm -e HONEYBADGER_PERSONAL_AUTH_TOKEN="HONEYBADGER_PERSONAL_AUTH_TOKEN" ghcr.io/honeybadger-io/honeybadger-mcp-server:latest

Add the following to youruser settingsor.vscode/mcp.jsonin your workspace:

{ "mcp": { "inputs": [ { "type": "promptString", "id": "honeybadger_auth_token", "description": "Honeybadger Personal Auth Token", "password": true } ], "servers": { "honeybadger": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "HONEYBADGER_PERSONAL_AUTH_TOKEN", "ghcr.io/honeybadger-io/honeybadger-mcp-server" ], "env": { "HONEYBADGER_PERSONAL_AUTH_TOKEN": "${input:honeybadger_auth_token}" } } } } }

SeeUse MCP servers in VS Codefor more info.

{ "context_servers": { "honeybadger": { "command": { "path": "docker", "args": [ "run", "-i", "--rm", "-e", "HONEYBADGER_PERSONAL_AUTH_TOKEN", "ghcr.io/honeybadger-io/honeybadger-mcp-server" ], "env": { "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token" } }, "settings": {} } } }

To build the Docker image and run it locally:

git clone git@github.com:honeybadger-io/honeybadger-mcp-server.git cd honeybadger-mcp-server docker build -t honeybadger-mcp-server .

Then you can replace "ghcr.io/honeybadger-io/honeybadger-mcp-server" with "honeybadger-mcp-server" in any of the configs above. Or you can run the image directly:

docker run -i --rm -e HONEYBADGER_PERSONAL_AUTH_TOKEN honeybadger-mcp-server

If you don't have Docker, you can build the server from source:

git clone git@github.com:honeybadger-io/honeybadger-mcp-server.git cd honeybadger-mcp-server go build -o honeybadger-mcp-server ./cmd/honeybadger-mcp-server

And then configure your MCP client to run the server directly:

{ "mcpServers": { "honeybadger": { "command": "/path/to/honeybadger-mcp-server", "args": ["stdio"], "env": { "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token" } } } }

Important: The server runs inread-only mode by defaultfor security. This means only read operations (likelist_projects,get_project,list_faults) are available. Write operations such ascreate_project,update_project, anddelete_projectare excluded to prevent accidental modifications.

To enable write operations, explicitly setHONEYBADGER_READ_ONLY=false.Use with cautionas this allows destructive operations like deleting projects.

The server defaults to Honeybadger's US API (https://app.honeybadger.io). If your account is in theEU region, setHONEYBADGER_API_URLtohttps://eu-app.honeybadger.ioand use a personal auth token from yourEU user settings. A US token won't authenticate against the EU region, and vice versa.

claude mcp add honeybadger-eu -- docker run -i --rm -e HONEYBADGER_PERSONAL_AUTH_TOKEN="your_eu_token" -e HONEYBADGER_API_URL="https://eu-app.honeybadger.io" ghcr.io/honeybadger-io/honeybadger-mcp-server:latest

# Run with custom configuration ./honeybadger-mcp-server stdio --auth-token your_token --log-level debug --api-url https://custom.honeybadger.io # Enable write operations (use with caution) ./honeybadger-mcp-server stdio --auth-token your_token --read-only=false # Get help ./honeybadger-mcp-server stdio --help

auth-token: "your_token_here" log-level: "info" api-url: "https://app.honeybadger.io" read-only: true

- get_reference- Returns Honeybadger reference documentation for LLMs, organized into non-overlapping topics:badgerql(query language),queries(Insights query fundamentals),charts(visualization views,chart_config),dashboards(widget schema, grid layout),alarms(trigger_configschema, states, patterns), anderrors(fault/notice model, error search syntax). Topics are fetched from thedocs siteand cached in memory. Tool descriptions declare which topics they require.

- topics: Reference topics to fetch, e.g.["badgerql", "charts"]. Use["all"]for everything; omit for an index of topics (array of strings, optional)

-

list_projects- List all Honeybadger projects

- account_id: Account ID to filter projects by specific account (string, optional)

get_project- Get detailed information for a single project by ID

- id: The ID of the project to retrieve (number, required)

create_project- Create a new Honeybadger project(requiresread-only=false)

- account_id: The account ID to associate the project with. If omitted, the project is created in the first account your auth token has access to (string, optional)
- name: The name of the new project (string, required)
- resolve_errors_on_deploy: Whether all unresolved faults should be marked as resolved when a deploy is recorded (boolean, optional)
- disable_public_links: Whether to allow fault details to be publicly shareable via a button on the fault detail page (boolean, optional)
- user_url: A URL format like 'http://example.com/admin/users/[user_id]' that will be displayed on the fault detail page (string, optional)
- source_url: A URL format like 'https://gitlab.com/username/reponame/blob/[sha]/[file]#L[line]' that is used to link lines in the backtrace to your git browser (string, optional)
- purge_days: The number of days to retain data (up to the max number of days available to your subscription plan) (number, optional)
- user_search_field: A field such as 'context.user_email' that you provide in your error context (string, optional)

update_project- Update an existing Honeybadger project(requiresread-only=false)

- id: The ID of the project to update (number, required)
- name: The name of the project (string, optional)
- resolve_errors_on_deploy: Whether all unresolved faults should be marked as resolved when a deploy is recorded (boolean, optional)
- disable_public_links: Whether to allow fault details to be publicly shareable via a button on the fault detail page (boolean, optional)
- user_url: A URL format like 'http://example.com/admin/users/[user_id]' that will be displayed on the fault detail page (string, optional)
- source_url: A URL format like 'https://gitlab.com/username/reponame/blob/[sha]/[file]#L[line]' that is used to link lines in the backtrace to your git browser (string, optional)
- purge_days: The number of days to retain data (up to the max number of days available to your subscription plan) (number, optional)
- user_search_field: A field such as 'context.user_email' that you provide in your error context (string, optional)

delete_project- Delete a Honeybadger project(requiresread-only=false)

- id: The ID of the project to delete (number, required)

get_project_occurrence_counts- Get occurrence counts for all projects or a specific project

- project_id: Project ID to get occurrence counts for a specific project (number, optional)
- period: Time period for grouping data: 'hour', 'day', 'week', or 'month'. Defaults to 'hour' (string, optional)
- environment: Environment name to filter results (string, optional)

get_project_integrations- Get a list of integrations (channels) for a Honeybadger project

- project_id: The ID of the project to get integrations for (number, required)

get_project_report- Get report data for a Honeybadger project

- project_id: The ID of the project to get report data for (number, required)
- report: The type of report to get: 'notices_by_class', 'notices_by_location', 'notices_by_user', or 'notices_per_day' (string, required)
- start: Start date/time in ISO 8601 format for the beginning of the reporting period (string, optional)
- stop: Stop date/time in ISO 8601 format for the end of the reporting period (string, optional)
- environment: Environment name to filter results (string, optional)

-

list_faults- Get a list of faults for a project with optional filtering and ordering. Fetch theerrorsreference topic (viaget_reference) for the fault/notice model and theqsearch syntax.

- project_id: The ID of the project to get faults for (number, required)
- q: Search string to filter faults (string, optional)
- created_after: Filter faults created after this timestamp (string, optional)
- occurred_after: Filter faults that occurred after this timestamp (string, optional)
- occurred_before: Filter faults that occurred before this timestamp (string, optional)
- limit: Maximum number of faults to return (max 25) (number, optional)
- order: Order results by 'recent' or 'frequent' (string, optional)
- page: Page number for pagination (number, optional)

get_fault- Get detailed information for a specific fault in a project

- project_id: The ID of the project containing the fault (number, required)
- fault_id: The ID of the fault to retrieve (number, required)

update_fault- Update a fault's resolved, ignored, assignee, or resolve-on-deploy state. Only the provided fields are changed.

- project_id: The ID of the project containing the fault (number, required)
- fault_id: The ID of the fault to update (number, required)
- resolved: Whether the fault is resolved (boolean, optional)
- ignored: Whether the fault is ignored (boolean, optional)
- assignee_id: Positive integer to assign that user; null to remove the current assignee; omit to leave unchanged (integer or null, optional)
- resolve_on_deploy: Mark the fault to be resolved automatically on next deploy (boolean, optional)

get_fault_counts- Get fault count statistics for a project with optional filtering. Fetch theerrorsreference topic (viaget_reference) for theqsearch syntax.

- project_id: The ID of the project to get fault counts for (number, required)
- q: Search string to filter faults (string, optional)
- created_after: Filter faults created after this timestamp (string, optional)
- occurred_after: Filter faults that occurred after this timestamp (string, optional)
- occurred_before: Filter faults that occurred before this timestamp (string, optional)

list_fault_notices- Get a list of notices (individual error events) for a specific fault

- project_id: The ID of the project containing the fault (number, required)
- fault_id: The ID of the fault to get notices for (number, required)
- created_after: Filter notices created after this timestamp (string, optional)
- created_before: Filter notices created before this timestamp (string, optional)
- limit: Maximum number of notices to return (max 25) (number, optional)

list_fault_affected_users- Get a list of users who were affected by a specific fault with occurrence counts

- project_id: The ID of the project containing the fault (number, required)
- fault_id: The ID of the fault to get affected users for (number, required)
- q: Search string to filter affected users (string, optional)

- query_insights- Execute a BadgerQL query against Insights data

- project_id: The ID of the project to query insights for (number, required)
- query: BadgerQL query string to execute against your Insights data (string, required)
- ts: Time range - shortcuts like 'today', 'week', or ISO 8601 duration (e.g., 'PT3H'). Defaults to PT3H (string, optional)
- timezone: IANA timezone identifier (e.g., 'America/New_York') for timestamp interpretation (string, optional)
- stream_ids: List of stream IDs to restrict the query to specific Insights streams. Uselist_streamsto discover a project's stream IDs. Omit to query all streams (array of strings, optional)

- list_streams- List Insights data streams for a project

- project_id: The ID of the project to list streams for (number, required)

-

list_dashboards- List all Insights dashboards for a project

- project_id: The ID of the project to list dashboards for (number, required)

get_dashboard- Get a single Insights dashboard by ID

- project_id: The ID of the project the dashboard belongs to (number, required)
- dashboard_id: The ID of the dashboard to retrieve (string, required)

create_dashboard- Create a new Insights dashboard(requiresread-only=false)

- project_id: The ID of the project to create the dashboard in (number, required)
- title: The title of the dashboard (string, required)
- widgets: JSON array of widget objects. Thedashboardsreference topic has the full widget schema and examples. Each widget needs atype(insights_vis,alarms,errors,deployments,checkins,uptime) and optionallygrid({x,y,w,h}),presentation({title, subtitle}), andconfig(type-specific settings) (string, required)
- default_ts: Default time range for the dashboard. ISO 8601 duration (e.g., P1D, PT3H) or keyword (today, yesterday, week, month) (string, optional)

update_dashboard- Update an existing Insights dashboard(requiresread-only=false)

- project_id: The ID of the project the dashboard belongs to (number, required)
- dashboard_id: The ID of the dashboard to update (string, required)
- title: The title of the dashboard (string, required)
- widgets: JSON array of widget objects (seecreate_dashboard) (string, required)
- default_ts: Default time range for the dashboard (string, optional)

delete_dashboard- Delete an Insights dashboard(requiresread-only=false)

- project_id: The ID of the project the dashboard belongs to (number, required)
- dashboard_id: The ID of the dashboard to delete (string, required)

-

list_alarms- List all Insights alarms for a project

- project_id: The ID of the project to list alarms for (number, required)

get_alarm- Get a single Insights alarm by ID

- project_id: The ID of the project the alarm belongs to (number, required)
- alarm_id: The ID of the alarm to retrieve (string, required)

create_alarm- Create a new Insights alarm(requiresread-only=false). Fetch reference topicsalarms,queries, andbadgerqlfirst (viaget_reference) for thetrigger_configschema and query guidelines.

- project_id: The ID of the project to create the alarm in (number, required)
- name: The name of the alarm (string, required)
- query: BadgerQL query for the alarm. The alarm system wraps the query to count results automatically (string, required)
- evaluation_period: How often the alarm is evaluated (e.g., 5m, 1h, 1d). Minimum 1m (string, required)
- trigger_config: JSON object defining when to trigger the alarm, e.g.{"type": "alert_result_count", "config": {"operator": "gt", "value": 10}}(string, required)
- lookback_lag: Delay before evaluating to allow data to arrive (e.g., 1m, or 0s for no lag) (string, required)
- description: Optional description of the alarm (string, optional)
- stream_ids: Optional JSON array of stream IDs to query (defaults to["default"]) (string, optional)

update_alarm- Update an existing Insights alarm(requiresread-only=false). Fetch reference topicsalarms,queries, andbadgerqlfirst (viaget_reference).

- project_id: The ID of the project the alarm belongs to (number, required)
- alarm_id: The ID of the alarm to update (string, required)
- name: The name of the alarm (string, required)
- query: BadgerQL query for the alarm (string, required)
- evaluation_period: How often the alarm is evaluated (e.g., 5m, 1h, 1d). Minimum 1m (string, required)
- trigger_config: JSON object defining when to trigger the alarm (string, required)
- lookback_lag: Delay before evaluating to allow data to arrive (e.g., 1m, 0s for no lag) (string, required)
- description: Optional description of the alarm (string, optional)
- stream_ids: Optional JSON array of stream IDs to query (string, optional)