Infrabase MCP server
ai.infrabase/directoryinfrabase.aistreamable-httpv1.0.0Scanned
Hand-verified AI infrastructure directory: tools, alternatives, EU providers, LLM API prices.
8 tools: 1 do something that can't be undone, 1 change things and 6 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. 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 Infrabase MCP server can do
The Infrabase MCP server is published by infrabase.ai, a domain the MCP Registry verified. It has 8 tools. It can do things that cannot be undone, such as sending, paying or publishing (request_featured_listing) and create or change data (1 tool: model_prices), but cannot delete data. 6 tools only read.
1 tool reads private data (search_tools).
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 11, 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.
8 tools
Can't be undone 1Claude Code: ask
request_featured_listingSends a featured-listing request for a product to Infrabase.ai.No findings
Why it is in this group
- The name "request_featured_listing" says "request": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
Description, as the server wrote it Sends a featured-listing request for a product to Infrabase.ai. Call it only after the user has confirmed. It sends their email address to Infrabase; a person replies by email. Calling it charges nothing.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Request a featured listing
Changes things 1Claude Code: ask
model_pricesVerified per-token prices for an AI model across hosting providers, ranked cheapest first by blended cost (3:1 input to output).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 Verified per-token prices for an AI model across hosting providers, ranked cheapest first by blended cost (3:1 input to output). Each row has input, output and cached prices per 1M tokens in the provider's own currency, the source pricing page and the date it was verified. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Model prices by provider
Only reads 6Show 6 read-only tools
featured_listing_infoReturns the price of an Infrabase.ai featured listing, the pages it appears on and what it does not change.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns the price of an Infrabase.ai featured listing, the pages it appears on and what it does not change. Read-only.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Featured listing info
find_alternativesFind alternatives to an AI infrastructure product listed on Infrabase.ai.No findings
Why it is in this group
- The name "find_alternatives" says "find": a word for reading.
Description, as the server wrote it Find alternatives to an AI infrastructure product listed on Infrabase.ai. Products doing the same primary job rank first, then products sharing a secondary job, then the rest of its categories. Returns the anchor product, the alternatives in that order and the total count. Data is hand-verified. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Find alternatives
get_toolGet the full Infrabase.ai record for one AI infrastructure product: description, jobs, pricing model and starting price, free trial, open source and licence, hosting, compliance (G…No findings
Why it is in this group
- The name "get_tool" says "get": a word for reading.
Description, as the server wrote it Get the full Infrabase.ai record for one AI infrastructure product: description, jobs, pricing model and starting price, free trial, open source and licence, hosting, compliance (GDPR, SOC 2, HIPAA), HQ country, icon, a screenshot of its site and links. Data is hand-verified. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get tool details
list_european_providersList AI infrastructure providers headquartered in Europe, for data residency and sovereignty questions.No findings
Why it is in this group
- The name "list_european_providers" says "list": a word for reading.
Description, as the server wrote it List AI infrastructure providers headquartered in Europe, for data residency and sovereignty questions. Optionally narrow by category or job; results come in pages, with the total and the next offset. Data is hand-verified. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List European providers
list_modelsList every AI model with verified per-provider pricing on Infrabase.ai: its slug, how many providers have a verified price and the cheapest one.No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it List every AI model with verified per-provider pricing on Infrabase.ai: its slug, how many providers have a verified price and the cheapest one. The slug is accepted by model_prices, which returns the full price table. Data is hand-verified. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List models with verified prices
search_toolsSearch Infrabase.ai, a hand-verified directory of AI infrastructure products: inference APIs, GPU clouds, vector databases, agent frameworks, observability, gateways and more.Reads private dataNo findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "directory": it reads files.
Description, as the server wrote it Search Infrabase.ai, a hand-verified directory of AI infrastructure products: inference APIs, GPU clouds, vector databases, agent frameworks, observability, gateways and more. Filter by free text, category, job (what the product does) or European headquarters. Returns each product's name, slug, tagline, jobs, pricing model, HQ country, icon and links, plus the total match count. Each result's slug is accepted by get_tool and find_alternatives. CC-BY-4.0. Each result includes an infrabase_url for attribution.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Search AI infrastructure tools
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 20, 2026, 18:26 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
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://infrabase.ai/mcp: tools/list returned 8 tools to an anonymous client, including request_featured_listing (irreversible), model_prices (write)
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.
Tools2 changed.~2 changedView diff
- Changed:list_european_providersOnly readsdescriptioninputSchema
- Changed:request_featured_listingCan't be undoneinputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http directory https://infrabase.ai/mcpclaude mcp add --transport http directory https://infrabase.ai/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__directory__search_tools",
"mcp__directory__get_tool",
"mcp__directory__find_alternatives",
"mcp__directory__list_models",
"mcp__directory__list_european_providers",
"mcp__directory__featured_listing_info"
],
"ask": [
"mcp__directory__model_prices",
"mcp__directory__request_featured_listing"
],
"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 directory. Review it before you use it.
Capability tags behind 1 rule
- mcp__directory__search_tools 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/ai.infrabase/directory/verify?hash=8a0ee2a6f50a5e15478f47e14505b857d87b9114c64a45051124139ed009354d" | jq -e '.changed == false'Pinned hash 8a0ee2a6f50a, 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/ai.infrabase/directory/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.infrabase/directory)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
Infrabase MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Infrabase MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 2 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 Infrabase MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Infrabase MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: request_featured_listing.
What tools does the Infrabase MCP server have?
- 8 tools: 1 irreversible, 1 write, 6 read. request_featured_listing, model_prices, search_tools, get_tool, find_alternatives, list_models, list_european_providers and featured_listing_info.
Does the Infrabase MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Infrabase MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Infrabase MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.