CleanIngredients MCP server
io.github.burmanharry/cleaningredientsburmanharrystreamable-httpv1.0.0Scanned
Research China-origin botanicals, supplier evidence gaps, sourcing briefs and ingredient costs.
7 tools: 2 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 CleanIngredients MCP server can do
The CleanIngredients MCP server is published by the GitHub account burmanharry. It has 7 tools. It can create or change data (2 tools: calculate_landed_cost and build_sourcing_brief), but cannot delete data. 5 tools only read.
1 tool reads private data (search_ingredients); 2 tools bring in text other people can write (get_ingredient and get_evidence_coverage).
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.
Last scanned Nov 15, 2026, version 1.0.0.
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.
7 tools
Changes things 2Claude Code: ask
build_sourcing_briefGenerate an RFQ draft for a catalog ingredient.1 finding
Why it is in this group
- The description's first verb is "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "build_sourcing_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate an RFQ draft for a catalog ingredient. Returns text only: does not store personal data, submit an inquiry, contact a supplier or place an order. Review the draft before using the website inquiry form.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
calculate_landed_costEstimate total and per-kg cost from buyer-provided inputs.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estimate total and per-kg cost from buyer-provided inputs. All amounts must be in one currency. Duty is a total monetary amount, not a percentage. No live freight, duty or supplier quotes are fetched.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 5Show 5 read-only tools
calculate_active_costCompare assay-based ingredient costs.No findings
Why it is in this group
- The description's first verb is "compare": a word for reading.
Description, as the server wrote it Compare assay-based ingredient costs. Price is per kg; assay is percent (0 < assay <= 100); targetActiveMg is desired active mass per serving. This is formulation arithmetic, not dosage advice.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_evidence_coverageRead current coverage counts for the core ingredients, including confirmed offerings and source reviews.Reads text others writeNo findings
Why it is in this group
- The name "get_evidence_coverage" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.
Description, as the server wrote it Read current coverage counts for the core ingredients, including confirmed offerings and source reviews. These are directory counts, not market-wide statistics.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_ingredientGet a botanical ingredient's grades, species, buying considerations and published source reviews.Reads text others writeNo findings
Why it is in this group
- The name "get_ingredient" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get a botanical ingredient's grades, species, buying considerations and published source reviews. Use the slug from search_ingredients. Includes actual offering counts; does not imply availability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_ingredientsSearch CleanIngredients ingredient names, summaries and species notes.Reads private dataNo findings
Why it is in this group
- The name "search_ingredients" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "note": it reads notes.
Description, as the server wrote it Search CleanIngredients ingredient names, summaries and species notes. Includes core and later-stage research; returns status, source links and review dates. Empty query lists ingredients.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_supplier_researchSearch company-published botanical supplier research.No findings
Why it is in this group
- The name "search_supplier_research" says "search": a word for reading.
Description, as the server wrote it Search company-published botanical supplier research. Every result is an unconfirmed research lead with a source URL and outstanding evidence checks. No stock, price, sample or quote availability is implied.
Annotations the server declares
- 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 outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- 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 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://cleaningredients.co/api/mcp: tools/list returned 7 tools to an anonymous client, including calculate_landed_cost (write), build_sourcing_brief (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "build_sourcing_brief" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "generate": a word for a change.
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.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http cleaningredients https://cleaningredients.co/api/mcpclaude mcp add --transport http cleaningredients https://cleaningredients.co/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__cleaningredients__search_ingredients",
"mcp__cleaningredients__get_ingredient",
"mcp__cleaningredients__search_supplier_research",
"mcp__cleaningredients__get_evidence_coverage",
"mcp__cleaningredients__calculate_active_cost"
],
"ask": [
"mcp__cleaningredients__calculate_landed_cost",
"mcp__cleaningredients__build_sourcing_brief"
],
"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 cleaningredients. Review it before you use it.
Capability tags behind 3 rules
- mcp__cleaningredients__search_ingredients private-data
- mcp__cleaningredients__get_ingredient untrusted-input
- mcp__cleaningredients__get_evidence_coverage 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/io.github.burmanharry/cleaningredients/verify?hash=3ff7c34b4a59e5196e18b7096fe41ea5884da3eab0037d800ece5220d7559bdd" | jq -e '.changed == false'Pinned hash 3ff7c34b4a59, from Nov 15, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.burmanharry/cleaningredients/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.burmanharry/cleaningredients)Source: MCP Registry · repository. Synced Nov 15, 2026, 23:17 UTC.
CleanIngredients MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CleanIngredients MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 2 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 CleanIngredients MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CleanIngredients 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 CleanIngredients MCP server have?
- 7 tools: 2 write, 5 read. calculate_landed_cost, build_sourcing_brief, search_ingredients, get_ingredient, search_supplier_research, get_evidence_coverage and calculate_active_cost.
Does the CleanIngredients MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CleanIngredients MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the CleanIngredients MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.