Production errors your coding agent can read: search, stack traces, context, trends, resolve.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer followed by a Runheed agent key (al_...), from Settings > Agent keys. Not needed by clients that sign in with OAuth.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Returns one error group in full: message, status, counts, first and last seen, environment, agent context, the top stack frames and the latest breadcrumbs.
The error ID to get details for
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http runheed https://runheed.com/api/mcp
Headers
Authorization (optional, not in the config above): Bearer followed by a Runheed agent key (al_...), from Settings > Agent keys. Not needed by clients that sign in with OAuth.Returns one error group in full: message, status, counts, first and last seen, environment, agent context, the top stack frames and the latest breadcrumbs.
| Argument | Type | Description |
|---|---|---|
| errorId* | string | The error ID to get details for |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"errorId"
],
"properties": {
"errorId": {
"type": "string",
"description": "The error ID to get details for"
}
}
}Returns everything recorded around an error: every breadcrumb, platform, runtime, OS, environment, release, the affected user, the agent session and extra data.
| Argument | Type | Description |
|---|---|---|
| errorId* | string | The error ID to get context for |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"errorId"
],
"properties": {
"errorId": {
"type": "string",
"description": "The error ID to get context for"
}
}
}Returns a 0 to 100 health score for a project (or the whole workspace), errors in the last 24 hours, the unresolved count, the error rate, recent issues and recommendations.
| Argument | Type | Description |
|---|---|---|
| projectId | string | Project ID (uses default if not specified) |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"projectId": {
"type": "string",
"description": "Project ID (uses default if not specified)"
}
}
}Returns the error groups seen most recently, newest first, with status, type, message, event count, last-seen time and ID.
| Argument | Type | Description |
|---|---|---|
| limit | number | Number of recent errors to return |
| projectId | string | Filter by project ID |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "number",
"default": 10,
"maximum": 50,
"minimum": 1,
"description": "Number of recent errors to return"
},
"projectId": {
"type": "string",
"description": "Filter by project ID"
}
}
}Returns error statistics for the last 24 hours, 7 days or 30 days: total, new and resolved counts, the most frequent errors and the hourly error rate.
| Argument | Type | Description |
|---|---|---|
| period | string | Time period to analyze |
| projectId | string | Filter by project ID |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"period": {
"enum": [
"24h",
"7d",
"30d"
],
"type": "string",
"default": "24h",
"description": "Time period to analyze"
},
"projectId": {
"type": "string",
"description": "Filter by project ID"
}
}
}Marks an error group ignored, for known or expected errors, so new occurrences stop alerting. Returns a confirmation.
| Argument | Type | Description |
|---|---|---|
| reason | string | Reason for ignoring this error |
| errorId* | string | The error ID to ignore |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"errorId"
],
"properties": {
"reason": {
"type": "string",
"description": "Reason for ignoring this error"
},
"errorId": {
"type": "string",
"description": "The error ID to ignore"
}
}
}Marks an error group resolved, with an optional note such as the fixing commit. The group reopens on its own if the error happens again. Returns a confirmation.
| Argument | Type | Description |
|---|---|---|
| comment | string | Optional comment about the fix |
| errorId* | string | The error ID to resolve |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"errorId"
],
"properties": {
"comment": {
"type": "string",
"description": "Optional comment about the fix"
},
"errorId": {
"type": "string",
"description": "The error ID to resolve"
}
}
}Searches the workspace's error groups by text (type or message), status and project. Returns each matching group with its status, type, message, event count, last-seen time and ID.
| Argument | Type | Description |
|---|---|---|
| limit | number | Maximum number of errors to return |
| query | string | Search query to filter errors by message or type |
| status | string | Filter by error status |
| projectId | string | Filter by project ID |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "number",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "Maximum number of errors to return"
},
"query": {
"type": "string",
"description": "Search query to filter errors by message or type"
},
"status": {
"enum": [
"unresolved",
"resolved",
"ignored"
],
"type": "string",
"description": "Filter by error status"
},
"projectId": {
"type": "string",
"description": "Filter by project ID"
}
}
}Moves an ignored error group back to unresolved, so new occurrences alert again. Returns a confirmation.
| Argument | Type | Description |
|---|---|---|
| errorId* | string | The error ID to unignore |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"errorId"
],
"properties": {
"errorId": {
"type": "string",
"description": "The error ID to unignore"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 2, 2026.