Runheed
Production error tracking your coding agent can search, read and resolve over MCP
- Pricing
- Free trial
- Platforms
- API, Web
- Runs
- Remotely
- Version
- 1.0.1
- Listing updated
- 3 days ago
About Runheed
Runheed is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
Where most error trackers are built for people reading dashboards, this one is built so an agent can go from report to fix. Each event carries the stack trace with your own frames marked, breadcrumbs, request details and, if you set it, the agent session that wrote the code. Repeats fold into one issue by fingerprint, so an agent sees a single TypeError with a count rather than hundreds of alerts.
The loop is: the SDK reports an exception, the agent asks what broke today, reads the context, ships a fix and marks the issue resolved with the commit in the note. If it recurs, it reopens with the earlier note visible. SDKs exist for Node.js, TypeScript and Python, with a plain JSON endpoint for other stacks.
Plans are flat per workspace, over-limit events are rejected rather than billed, and it can run alongside Sentry. Authorization, cookie and API-key headers are redacted on arrival.
Install
Run in a terminal
claude mcp add --transport http runheed https://runheed.com/api/mcpAdd to Settings → Connectors → Add custom connector
https://runheed.com/api/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"runheed": {
"url": "https://runheed.com/api/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"runheed": {
"type": "http",
"url": "https://runheed.com/api/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"runheed": {
"serverUrl": "https://runheed.com/api/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"runheed": {
"type": "http",
"url": "https://runheed.com/api/mcp"
}
}
}Tools this server provides (9)
Taken from the project documentation; the running server may differ.
- runheed_search_errors
- Searches production errors.
- runheed_get_error
- Fetches one error.
- runheed_get_error_context
- Fetches the stack trace and surrounding context for an error.
- runheed_get_recent
- Lists recent errors.
- runheed_get_trends
- Shows error trends.
- runheed_get_project_health
- Reports the health of a project.
- runheed_resolve_error
- Marks an error resolved.
- runheed_ignore_error
- Ignores an error.
- runheed_unignore_error
- Stops ignoring an error.
What it does
- Agent-readable errors
- Stack traces, breadcrumbs and request details served through MCP.
- Grouping and regressions
- Repeats merge into one issue and resolved errors reopen on recurrence.
- Agent context
- Records which agent and session shipped the failing code.
- Resolve from the agent
- The agent closes an issue with the fixing commit noted.
- Redaction
- Secret headers are redacted on arrival.
- Many SDKs
- Node, Python and a JSON endpoint, with setup guides for many frameworks.
Good for
- Ask Claude Code what broke in production today
- Have an agent fix and close a recurring error
- Track errors in apps an AI agent built
- Run next to Sentry for an agent-friendly view
Pricing
Free trial, from $29 a month
7-day trial with card up front; Solo $29/mo, Pro $79/mo, Scale $199/mo
Prices change. Check runheed.com before you buy.
Runheed FAQ
What does it cost?
Solo $29/mo, Pro $79/mo and Scale $199/mo, each with a 7-day trial.
What happens over the event limit?
Events are rejected, never charged as overage.
Can I try it without signing up?
Yes, sample errors can be explored in your own agent with no signup.
Does it replace Sentry?
No, it is described as working alongside it.
Is Runheed free?
Runheed is a paid product with a free trial. Paid plans start at $29 a month.
How do I add Runheed to Claude Code?
Run this command in your terminal: claude mcp add --transport http runheed https://runheed.com/api/mcp
What are the best alternatives to Runheed?
The closest alternatives to Runheed are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Runheed

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools