Runheed MCP server
com.runheed/runheedrunheed.comstreamable-httpv1.0.2Scanned
Production errors your coding agent can read: search, stack traces, releases, resolve, setup.
9 tools: 3 change things and 6 only read.
- Reads private data · 4
- Reads text others write · 4
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Runheed MCP server can do
The Runheed MCP server is published by runheed.com, a domain the MCP Registry verified. It has 9 tools. It can create or change data (3 tools: runheed_resolve_error, runheed_ignore_error and runheed_unignore_error), but cannot delete data. 6 tools only read.
4 tools read private data (runheed_search_errors, runheed_get_error, runheed_get_recent and 1 more); 4 tools bring in text other people can write (runheed_search_errors, runheed_get_error, runheed_get_recent and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 6, 2026, version 1.0.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
9 tools
Changes things 3Claude Code: ask
runheed_ignore_errorMarks an error group ignored, for known or expected errors, so new occurrences stop alerting.No findings
Why it is in this group
- The description's first verb is "mark": a word for a change.
Description, as the server wrote it Marks an error group ignored, for known or expected errors, so new occurrences stop alerting. Returns a confirmation.
Annotations the server declares
- title: Ignore an error
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
runheed_resolve_errorMarks an error group resolved, with an optional note such as the fixing commit.Reads private dataNo findings
Why it is in this group
- The name "runheed_resolve_error" says "resolve": a word for reading.
- The description's first verb is "mark": a word for a change.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it 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.
Annotations the server declares
- title: Resolve an error
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
runheed_unignore_errorMoves an ignored error group back to unresolved, so new occurrences alert again.No findings
Why it is in this group
- The description's first verb is "move": a word for a change.
Description, as the server wrote it Moves an ignored error group back to unresolved, so new occurrences alert again. Returns a confirmation.
Annotations the server declares
- title: Stop ignoring an error
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
runheed_get_errorReturns one error group in full: message, status, counts, first and last seen, environment, agent context, the top stack frames and the latest breadcrumbs.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "runheed_get_error" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "return" and "message": it reads messages, which other people can write.
Description, as the server wrote 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.
Annotations the server declares
- title: Get an error
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
runheed_get_error_contextReturns everything recorded around an error: every breadcrumb, platform, runtime, OS, environment, release, the affected user, the agent session and extra data.No findings
Why it is in this group
- The name "runheed_get_error_context" says "get": a word for reading.
Description, as the server wrote it Returns everything recorded around an error: every breadcrumb, platform, runtime, OS, environment, release, the affected user, the agent session and extra data.
Annotations the server declares
- title: Get error context
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
runheed_get_project_healthReturns 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.Reads text others writeNo findings
Why it is in this group
- The name "runheed_get_project_health" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "issue": it reads issues, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get project health
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
runheed_get_recentReturns the error groups seen most recently, newest first, with status, type, message, route, top stack frame, event count, last-seen time and ID.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "runheed_get_recent" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "return" and "message": it reads messages, which other people can write.
Description, as the server wrote it Returns the error groups seen most recently, newest first, with status, type, message, route, top stack frame, event count, last-seen time and ID.
Annotations the server declares
- title: Get recent errors
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
runheed_get_trendsReturns 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.No findings
Why it is in this group
- The name "runheed_get_trends" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get error trends
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
runheed_search_errorsSearches the workspace's error groups by text (type, message, route, file or extra data), status and project.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "runheed_search_errors" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "search" and "message": it reads messages, which other people can write.
Description, as the server wrote it Searches the workspace's error groups by text (type, message, route, file or extra data), status and project. Returns each matching group with its status, type, message, route, top stack frame, event count, last-seen time and ID.
Annotations the server declares
- title: Search errors
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data4
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 17, 2026, 15:22 UTC, unchanged since Nov 17, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://runheed.com/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://runheed.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (2 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://runheed.com/api/mcp: tools/list returned 13 tools to an anonymous client, including runheed_merge_errors (irreversible), runheed_send_test_event (irreversible), runheed_resolve_error (write), runheed_ignore_error (write), runheed_unignore_error (write) and 1 more
Posture changes
- Nov 17, 2026
- Tools that change things, listed without credentials: 3 to 6
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 6.View diff
- Tools that change things, listed without credentials: 3 to 6
Tools4 changed.~4 changedView diff
- Changed:runheed_get_project_healthOnly readsinputSchema
- Changed:runheed_get_recentOnly readsdescriptioninputSchema
- Changed:runheed_get_trendsOnly readsinputSchema
- Changed:runheed_search_errorsOnly readsdescriptioninputSchema
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http runheed https://runheed.com/api/mcpclaude mcp add --transport http runheed https://runheed.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__runheed__runheed_search_errors",
"mcp__runheed__runheed_get_error",
"mcp__runheed__runheed_get_recent",
"mcp__runheed__runheed_get_trends",
"mcp__runheed__runheed_get_error_context",
"mcp__runheed__runheed_get_project_health"
],
"ask": [
"mcp__runheed__runheed_resolve_error",
"mcp__runheed__runheed_ignore_error",
"mcp__runheed__runheed_unignore_error"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as runheed. Review it before you use it.
Capability tags behind 5 rules
- mcp__runheed__runheed_search_errors private-data, untrusted-input
- mcp__runheed__runheed_get_error private-data, untrusted-input
- mcp__runheed__runheed_get_recent private-data, untrusted-input
- mcp__runheed__runheed_resolve_error private-data
- mcp__runheed__runheed_get_project_health untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.runheed/runheed/verify?hash=2b1a644fee27b358353549b11ec169ba837c8083fad772aa4cc8ec75a4fa43f7" | jq -e '.changed == false'Pinned hash 2b1a644fee27, from Nov 6, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.runheed/runheed/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.runheed/runheed)Source: MCP Registry · repository. Synced Nov 20, 2026, 04:17 UTC.
Runheed MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Runheed MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Runheed MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Runheed MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Runheed MCP server have?
- 9 tools: 3 write, 6 read. runheed_resolve_error, runheed_ignore_error, runheed_unignore_error, runheed_search_errors, runheed_get_error, runheed_get_recent, runheed_get_trends, runheed_get_error_context and 1 more.
Does the Runheed MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Runheed MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Runheed MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.