InferIndex MCP server
io.github.InferIndex/inferindexInferIndexstreamable-httpv1.0.1Scanned
LLM API prices across 100+ providers: cheapest offer, comparisons, history and cost estimates.
9 tools: 1 do something that can't be undone, 5 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- 1 finding
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 InferIndex MCP server can do
The InferIndex MCP server is published by the GitHub account InferIndex. It has 9 tools. It can do things that cannot be undone, such as sending, paying or publishing (price_history) and create or change data (5 tools: cheapest, estimate_cost, provider_ranking, gpu_rentals and 1 more), but cannot delete data. 3 tools only read.
1 tool can send data out of your system (price_history).
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 13, 2026, version 1.0.1.
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.
9 tools
Can't be undone 1Claude Code: ask
price_historyPrice history of one model: every offer tracked by InferIndex (daily or weekly min/max/last price in USD, or raw price changes), plus the official price of the model's lab over tim…Can send data out1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "price_history" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Price history of one model: every offer tracked by InferIndex (daily or weekly min/max/last price in USD, or raw price changes), plus the official price of the model's lab over time. Give either days, or from/to (YYYY-MM-DD), or at (a date) for the prices in effect that day.
Annotations the server declares
- title: Price history of a model
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 5Claude Code: ask
cheapestCheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1).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 Cheapest current API offers for one model across direct providers and aggregators, in USD per 1M tokens (input, output, blended 3:1). Stale prices, and flex/batch tiers, are excluded by default. Optional filters (context, tools, JSON, vision, region, no training on prompts, open sign-up) and usage (tokens per request, requests per day) to get an estimated cost per request and per month. Returns the winner in detail and one short line per following offer. A condition that is absent was not published by the provider, it never means "no"; a flag not listed in signals is false.
Annotations the server declares
- title: Cheapest offers for a model
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimate_costEstimated cost of a workload on one model at each provider: cost per request, and per month if requests_per_day is given, taking the provider's tiered pricing and prompt-cache pric…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 Estimated cost of a workload on one model at each provider: cost per request, and per month if requests_per_day is given, taking the provider's tiered pricing and prompt-cache price into account. Offers sorted by estimated cost, cheapest first: the cheapest in detail, then one short line per offer with its estimated cost.
Annotations the server declares
- title: Estimate the cost of a workload
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
gpu_rentalsRental offers for one GPU type: provider, price in USD per GPU per hour, number of GPUs in the published configuration, billing and region when published.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 Rental offers for one GPU type: provider, price in USD per GPU per hour, number of GPUs in the published configuration, billing and region when published. One block per tier (guaranteed, community, spot), each with its own cheapest offer, also given per configuration (cheapest_by_gpu_count: the price per GPU of a single GPU and of a multi-GPU node are not comparable); tiers are never compared with each other. guaranteed: capacity the provider presents as not interrupted; community: third-party hosts; spot: interruptible capacity. Prices are as published by the provider, and dated. Get the GPU id from list_gpus.
Annotations the server declares
- title: Rental offers for one GPU, by tier
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
provider_rankingProviders ranked by how far below or above the market their prices are: each provider's median gap to the market, in percent (score_pct, negative when below the market), where the …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 Providers ranked by how far below or above the market their prices are: each provider's median gap to the market, in percent (score_pct, negative when below the market), where the market of a model is the median blended 3:1 price of its providers, counted only on models with at least min_providers comparable providers (models_measured). Also the number of models where the provider holds the offer the cheapest tool would select (cheapest_count). Ranked from min_models models measured; refreshed every hour.
Annotations the server declares
- title: Providers ranked by price gap
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
self_host_or_apiIs it cheaper to host an open-weights model yourself on rented GPUs, or to use the cheapest API offer?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 Is it cheaper to host an open-weights model yourself on rented GPUs, or to use the cheapest API offer? Returns a one-sentence verdict (headline) and the numbers behind it: the break-even volume in million tokens per day, the throughput the whole configuration must deliver for self-hosting to cost less (required_tokens_per_second: compare it with what your setup does), the break-even utilization when a throughput is known, the GPU configuration and its hourly price, and what the verdict rests on (confidence). Without a volume you still get the verdict and the break-even volume. It is an estimate: the throughput is a published measurement (measured), an estimate scaled from one (derived; estimated for a wide range), or a published minimum (lower_bound: a floor, valid for requests of up to 2,048 tokens in total, that can show self-hosting wins, never that the API is cheaper); or you give your own tokens_per_second. When no published figure decides, the headline gives the break-even volume and the required throughput, to compare with yours, rather than a yes or no, and may point out a dearer setup that published figures do decide (settled_alternative: for comparison, not a recommendation). headline_kind and headline_values give the headline as fields. It declines to give a number (status refused, with a reason) when it cannot do so reliably, for example a closed model, weights that do not fit the requested GPU, or a GPU nobody rents. Hardware rental only: the hourly price the provider publishes for the machine. It does not count the engineering to deploy and run the model, monitoring, redundancy, start-up time, or storage and network costs billed separately.
Annotations the server declares
- title: Self-host an open model or use the API?
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 3Show 3 read-only tools
compare_providersCurrent offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, quantization, signals and training on prom…No findings
Why it is in this group
- The name "compare_providers" says "compare": a word for reading.
Description, as the server wrote it Current offers for one model, one line per provider and source (direct or via an aggregator), cheapest first (10 by default), with price, quantization, signals and training on prompts when published; the cheapest offer comes in detail. Pass detail: "full" for context, every published condition (data regions, sign-up) and reliability from official status pages on each offer.
Annotations the server declares
- title: Compare providers for a model
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_gpusGPU types whose rental price InferIndex tracks (H100, A100, L40S…), with the lowest price per GPU per hour in USD for each tier (guaranteed, community, spot) and the number of GPUs…No findings
Why it is in this group
- The name "list_gpus" says "list": a word for reading.
Description, as the server wrote it GPU types whose rental price InferIndex tracks (H100, A100, L40S…), with the lowest price per GPU per hour in USD for each tier (guaranteed, community, spot) and the number of GPUs of that configuration. Prices are per GPU per hour, as published by each provider, and dated. Tiers are different products and are never compared with each other.
Annotations the server declares
- title: GPU types tracked for rental prices
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_modelsFind the exact id of an LLM tracked by InferIndex from a name or partial name (e.g.No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Find the exact id of an LLM tracked by InferIndex from a name or partial name (e.g. 'deepseek', 'qwen3 max', 'claude opus'). Returns matching model ids and names, best match first.
Annotations the server declares
- title: Search models
- 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 private-data or untrusted-input.
- 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 out1
- 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, 18:58 UTC, unchanged since Oct 29, 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
- 6
- 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 6 tools that change things (1 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.inferindex.dev/mcp: tools/list returned 9 tools to an anonymous client, including price_history (irreversible), cheapest (write), estimate_cost (write), provider_ranking (write), gpu_rentals (write) and 1 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 5 to 6
Findings
Matches of fixed checks, with the text they matched.
- Warnprice_history
The server marks "price_history" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input addresses people (input.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added.+1 addedView diff
- Added:provider_rankingChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6.View diff
- Tools that change things, listed without credentials: 5 to 6
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcpclaude mcp add --transport http inferindex https://mcp.inferindex.dev/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__inferindex__search_models",
"mcp__inferindex__compare_providers",
"mcp__inferindex__list_gpus"
],
"ask": [
"mcp__inferindex__cheapest",
"mcp__inferindex__price_history",
"mcp__inferindex__estimate_cost",
"mcp__inferindex__provider_ranking",
"mcp__inferindex__gpu_rentals",
"mcp__inferindex__self_host_or_api"
],
"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 inferindex. Review it before you use it.
Capability tags behind 1 rule
- mcp__inferindex__price_history outbound
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.InferIndex/inferindex/verify?hash=4d38cb0c302cd5eec671ebf198c47df4e0221959de7ca9cc1c4debe6f103c020" | jq -e '.changed == false'Pinned hash 4d38cb0c302c, from Nov 13, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.InferIndex/inferindex/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.InferIndex/inferindex)Source: MCP Registry · repository. Synced Nov 13, 2026, 18:17 UTC.
InferIndex MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the InferIndex MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 6 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 InferIndex MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the InferIndex MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: price_history.
What tools does the InferIndex MCP server have?
- 9 tools: 1 irreversible, 5 write, 3 read. price_history, cheapest, estimate_cost, provider_ranking, gpu_rentals, self_host_or_api, search_models, compare_providers and 1 more.
Does the InferIndex MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the InferIndex MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): price_history.
Has the InferIndex MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.