runchr MCP server
io.github.rmngl/runchrrmnglstreamable-httpv0.1.2Scanned
A curated registry of agent stacks: search by job, get the tools, prompt, and install plan.
4 tools: 1 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the runchr MCP server can do
The runchr MCP server is published by the GitHub account rmngl. It has 4 tools. It can create or change data (1 tool: get_manifest), but cannot delete data. 3 tools only read.
1 tool reads private data (get_install_plan).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 0.1.2.
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.
4 tools
Changes things 1Claude Code: ask
get_manifestThe manifest a loader runs: the tools, the model, the harness, and the prompt.1 finding
Why it is in this group
- The name "get_manifest" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "get_manifest" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_manifest" says "get": a word for reading.
Description, as the server wrote it The manifest a loader runs: the tools, the model, the harness, and the prompt. This is the thing to install.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 3Show 3 read-only tools
get_install_planHow to install a stack: the MCP servers to configure, the shell commands to run, and the notes (a path, a harness command) for the rest.Reads private dataNo findings
Why it is in this group
- The name "get_install_plan" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it How to install a stack: the MCP servers to configure, the shell commands to run, and the notes (a path, a harness command) for the rest. Deciding and configuring are open; the agent's host runs the commands.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_stackOne stack's card: its copy, its tools, its tier, and its revision.No findings
Why it is in this group
- The name "get_stack" says "get": a word for reading.
Description, as the server wrote it One stack's card: its copy, its tools, its tier, and its revision.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
search_stacksFind agent stacks by problem domain or text.No findings
Why it is in this group
- The name "search_stacks" says "search": a word for reading.
Description, as the server wrote it Find agent stacks by problem domain or text. A query is split into words and any of them may match, against the name, the copy, and the prompt. When nothing matches, the reply is labelled and filled with the most established stacks.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- 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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 21, 2026, 19:22 UTC, unchanged since Nov 7, 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.runchr.com/mcp: tools/list returned 4 tools to an anonymous client, including get_manifest (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnget_manifest
The server marks "get_manifest" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "get_manifest" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 changed.~4 changedView diff
- Changed:get_install_planOnly readsannotations
- Changed:get_manifestChanges thingsannotations
- Changed:get_stackOnly readsannotations
- Changed:search_stacksOnly readsdescriptioninputSchemaannotations
Install
Pinned to version 0.1.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http runchr https://api.runchr.com/mcpclaude mcp add --transport http runchr https://api.runchr.com/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__runchr__search_stacks",
"mcp__runchr__get_stack",
"mcp__runchr__get_install_plan"
],
"ask": [
"mcp__runchr__get_manifest"
],
"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 runchr. Review it before you use it.
Capability tags behind 1 rule
- mcp__runchr__get_install_plan private-data
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/io.github.rmngl/runchr/verify?hash=1464f2644c9ae319cfae516ead4e6a8187ec14e97f67641c728ef123dad7b5b2" | jq -e '.changed == false'Pinned hash 1464f2644c9a, from Nov 20, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.rmngl/runchr/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.rmngl/runchr)Source: MCP Registry. Synced Nov 6, 2026, 13:18 UTC.
runchr MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the runchr MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the runchr MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the runchr 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 runchr MCP server have?
- 4 tools: 1 write, 3 read. get_manifest, search_stacks, get_stack and get_install_plan.
Does the runchr MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the runchr MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the runchr 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.