WildRun AI

com.wildrunai/wildrunaiwildrunai.comstreamable-httpv1.0.0Scanned 1 hour ago

SEO, AEO and GEO service for Bend and Central Oregon, plus the article archive as Markdown.

3 tools: 1 can delete or cancel things and 2 only read.

Reads private data · 1
Reads text others write · 0
Can send data out · 0
2 findings

Anlyon alternative

1 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 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 →

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.

3 tools

Deletes or cancels 1Removes, cancels or revokes something.Claude Code: deny

list_articlesThe archive of published articles, newest first: slug, title, description, topic cluster, date and URLs.2 findings
Why it is in this group
- The name "list_articles" says "list": a word for reading.
- The description's first verb is "archive": a word for removing or ending something.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
  The server marks "list_articles" read-only (readOnlyHint: true), and its own name, description or input give the class "destructive".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "list_articles" says "list": a word for reading.
  What this check looks for
- Warn
  The server marks "list_articles" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "list_articles" says "list": a word for reading.
  What this check looks for
Description, as the server wrote it
The archive of published articles, newest first: slug, title, description, topic cluster, date and URLs. Use this to find something to read before calling get_article.
Annotations the server declares
- title: List articles
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 2Looks things up and changes nothing.Show 2 read-only tools

get_articleThe full text of one article as Markdown, by slug (get slugs from list_articles).No findings
Why it is in this group
- The name "get_article" says "get": a word for reading.
Description, as the server wrote it
The full text of one article as Markdown, by slug (get slugs from list_articles). Roughly a third of the bytes of the HTML page.
Annotations the server declares
- title: Read an article
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_service_linesWildRun AI’s one service — managed SEO + AEO + GEO for businesses in Bend and Central Oregon — with its page, scope-and-pricing section, free audit request and contact page.Reads private dataNo findings
Why it is in this group
- The name "get_service_lines" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "contact": it reads contacts.
Description, as the server wrote it
WildRun AI’s one service — managed SEO + AEO + GEO for businesses in Bend and Central Oregon — with its page, scope-and-pricing section, free audit request and contact page. Managed work is scoped and quoted after the free audit. Page URLs also answer 'Accept: text/markdown'.
Annotations the server declares
- title: Service lines
- readOnlyHint: true
- destructiveHint: false
- 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.; get_service_lines
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.

Findings

Matches of fixed checks, with the text they matched.

2 warn

Warnlist_articles
The server marks "list_articles" read-only (readOnlyHint: true), and its own name, description or input give the class "destructive".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "list_articles" says "list": a word for reading.
What this check looks for
Warnlist_articles
The server marks "list_articles" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "list_articles" says "list": a word for reading.
What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http wildrunai https://wildrunai.com/mcp

claude mcp add --transport http wildrunai https://wildrunai.com/mcp

Run 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.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__wildrunai__get_service_lines",
      "mcp__wildrunai__get_article"
    ],
    "ask": [],
    "deny": [
      "mcp__wildrunai__list_articles"
    ]
  }
}

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 wildrunai. Review it before you use it.

Capability tags behind 1 rule

mcp__wildrunai__get_service_lines private-data

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://anlyon.dev/api/v1/servers/com.wildrunai/wildrunai/verify?hash=28ac0fa37c17b0c5455f40d3078566ccd765ff3efd3b2bb04e97a35e69f5c631" | jq -e '.changed == false'

Pinned hash 28ac0fa37c17, from Oct 26, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/com.wildrunai/wildrunai/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/com.wildrunai/wildrunai.svg)](https://anlyon.dev/servers/com.wildrunai/wildrunai)

Source: MCP Registry. Synced Oct 26, 2026, 22:17 UTC.