Safe Bite MCP server
io.github.AndrewVG23/safe-biteAndrewVG23streamable-httpv1.0.4Scanned
Restaurant inspections for Chicago, NYC, Minneapolis, Milwaukee, Austin, and Denver.
5 tools: 5 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Safe Bite MCP server can do
The Safe Bite MCP server is published by the GitHub account AndrewVG23. It has 5 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
None of its tools reads private data, brings in text other people write, or sends data out.
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 2 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.4.
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.
5 tools
Only reads 5Show 5 read-only tools
find_nearby_restaurantsReturns an MCP App card of restaurants near a point or address.No findings
Why it is in this group
- The name "find_nearby_restaurants" says "find": a word for reading.
Description, as the server wrote it Returns an MCP App card of restaurants near a point or address. The default radius is a quarter mile.
get_city_inspectionsReturns an MCP App card ranking restaurants with the most serious recent health-inspection violations in the chosen city (chicago, nyc, minneapolis, milwaukee, austin, denver).No findings
Why it is in this group
- The name "get_city_inspections" says "get": a word for reading.
Description, as the server wrote it Returns an MCP App card ranking restaurants with the most serious recent health-inspection violations in the chosen city (chicago, nyc, minneapolis, milwaukee, austin, denver). The server ranks a wide recent window and returns one page of that ranking. Supports limit/offset pagination.
get_milwaukee_inspectionsReturns an MCP App card ranking Milwaukee restaurants with the most serious recent health-inspection violations.No findings
Why it is in this group
- The name "get_milwaukee_inspections" says "get": a word for reading.
Description, as the server wrote it Returns an MCP App card ranking Milwaukee restaurants with the most serious recent health-inspection violations. The server ranks a wide recent window and returns one page of that ranking. Supports limit/offset pagination.
search_restaurantsLooks up restaurants by name, including partial names and imperfect spelling, and returns an MCP App card for each match.No findings
Why it is in this group
- The name "search_restaurants" says "search": a word for reading.
Description, as the server wrote it Looks up restaurants by name, including partial names and imperfect spelling, and returns an MCP App card for each match. An optional city argument limits the search to one city.
show_inspectionReturns an MCP App card for a restaurant name, or a map for a violation term in a city.No findings
Why it is in this group
- The name "show_inspection" says "show": a word for reading.
Description, as the server wrote it Returns an MCP App card for a restaurant name, or a map for a violation term in a city. Hosts that support MCP Apps render the card or map inline. The text result names the matches for hosts that only show text.
Annotations the server declares
- 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 private-data or untrusted-input or outbound.
- Reads private data0
- 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 20, 2026, 18:56 UTC, unchanged since Oct 22, 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
- 0
- 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
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.
Tools5 changed.~5 changedView diff
- Changed:find_nearby_restaurantsOnly readsdescription
- Changed:get_city_inspectionsOnly readsdescriptioninputSchema
- Changed:get_milwaukee_inspectionsOnly readsdescriptioninputSchema
- Changed:search_restaurantsOnly readsdescription
- Changed:show_inspectionOnly readsdescription
Tools1 added, 4 changed.+1 added~4 changedView diff
- Added:show_inspectionOnly reads
- Changed:find_nearby_restaurantsOnly readsdescription
- Changed:get_city_inspectionsOnly readsdescription
- Changed:get_milwaukee_inspectionsOnly readsdescription
- Changed:search_restaurantsOnly readsdescription
Install
Pinned to version 1.0.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http safe-bite https://www.safebiter.com/mcpclaude mcp add --transport http safe-bite https://www.safebiter.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__safe-bite__show_inspection",
"mcp__safe-bite__get_milwaukee_inspections",
"mcp__safe-bite__get_city_inspections",
"mcp__safe-bite__search_restaurants",
"mcp__safe-bite__find_nearby_restaurants"
],
"ask": [],
"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 safe-bite. Review it before you use it.
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.AndrewVG23/safe-bite/verify?hash=c16c7a94e2451ee38b1f427ad3e14ae9930beb941ba5531f67d3955b6d4e1fb5" | jq -e '.changed == false'Pinned hash c16c7a94e245, from Nov 11, 2026, 19:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.AndrewVG23/safe-bite/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.AndrewVG23/safe-bite)Source: MCP Registry · repository. Synced Nov 11, 2026, 19:17 UTC.
Safe Bite MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Safe Bite MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Safe Bite MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Safe Bite 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 Safe Bite MCP server have?
- 5 tools: 5 read. show_inspection, get_milwaukee_inspections, get_city_inspections, search_restaurants and find_nearby_restaurants.
Does the Safe Bite MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Safe Bite MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Safe Bite MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.