inferenceindexer-mcp server
io.github.DesMartin01/inferenceindexer-mcpDesMartin01streamable-httpv0.1.1Scanned
AI inference pricing for agents: live and historical model prices, provider comparison.
10 tools: 1 change things and 9 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
1 tool here changes things. 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 inferenceindexer-mcp server can do
The inferenceindexer-mcp server is published by the GitHub account DesMartin01. It has 10 tools. It can create or change data (1 tool: recommend_models), but cannot delete data. 9 tools only read.
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.
Last scanned Nov 15, 2026, version 0.1.1.
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.
10 tools
Changes things 1Claude Code: ask
recommend_modelsRecommend the best-value AI models for given constraints, ranked with receipts.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.
Description, as the server wrote it Recommend the best-value AI models for given constraints, ranked with receipts. The core answer endpoint: give it constraints and it returns the top models ranked by Cost/IQ (quality-adjusted price, lower is better), each with a plain-English 'why', a hot-swap endpoint_config (provider base_url + native model id, ready to call), as-of timestamps, and runner-ups. Args: budget_max_usd_per_m: Max blended price $/M (optional). context_min: Minimum context window in tokens (optional). modality: 'text' (default), 'vision', or 'any'. zdr: Require zero-data-retention providers (optional). eu_sovereign: Require EU-sovereign providers (optional). reasoning: Filter reasoning models (null = any, true/false). aa_min: Hard floor on the AA Intelligence Index score (quality gate). use_case: Task profile: support | volume | extraction | summarization | coding | research. prefer_callable: Demote models without a verified call recipe below callable ones. limit: Max recommendations (1-20, default 5). Returns: ranked recommendations with endpoint_config and ranking evidence.
Only reads 9Show 9 read-only tools
compare_providersCompare the price of one model across the providers that host it.No findings
Why it is in this group
- The name "compare_providers" says "compare": a word for reading.
Description, as the server wrote it Compare the price of one model across the providers that host it. Args: model_id: Canonical model id, e.g. 'meta/muse-spark-1.1'. Returns: per-provider endpoints with pricing, showing where direct provider prices diverge (e.g. from OpenRouter's negotiated rate).
explain_modelGet everything about one model in a single call: the full picture.No findings
Why it is in this group
- The name "explain_model" says "explain": a word for reading.
Description, as the server wrote it Get everything about one model in a single call: the full picture. Returns current pricing (input/output/blended, Cost/IQ, 24h/7d changes), a price-history summary with trend, all provider endpoints, the cheapest hand-verified endpoint with its native model id (for hot-swapping), privacy flags (ZDR/EU availability), and the AA intelligence score. Everything is as-of stamped. Args: model_id: Canonical model id, e.g. 'anthropic/claude-sonnet-5'. history_days: Price-history window (default 30, max 365). Returns: complete model profile with pricing, endpoints, privacy, quality.
get_composite_historyGet SIT-Composite index history / trend over time.No findings
Why it is in this group
- The name "get_composite_history" says "get": a word for reading.
Description, as the server wrote it Get SIT-Composite index history / trend over time. Args: days: History window in days (1-90, default 30). Returns: historical composite index values.
get_composite_latestGet the current SIT-Composite index value + per-tier breakdown.No findings
Why it is in this group
- The name "get_composite_latest" says "get": a word for reading.
Description, as the server wrote it Get the current SIT-Composite index value + per-tier breakdown. The SIT-Composite is a usage-weighted mean of the top-50 models by token volume, reflecting what developers actually pay for inference.
get_modelGet full detail + current pricing for one model by its id.No findings
Why it is in this group
- The name "get_model" says "get": a word for reading.
Description, as the server wrote it Get full detail + current pricing for one model by its id. Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6' or 'anthropic/claude-sonnet-5'. Returns: pricing, tier, SIT score, quality-adjusted price (Cost/IQ).
get_model_historyGet HISTORICAL price data / trends for one model.No findings
Why it is in this group
- The name "get_model_history" says "get": a word for reading.
Description, as the server wrote it Get HISTORICAL price data / trends for one model. This is InferenceIndexer's differentiator: aggregators like OpenRouter expose only current price; this returns the price over time (input, output, blended $/M), enabling trend analysis. Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6'. days: History window in days (1-365, default 30; plan-dependent). Returns: historical price series for the model.
get_providerGet detail for one provider: models, tier breakdown, price range.No findings
Why it is in this group
- The name "get_provider" says "get": a word for reading.
Description, as the server wrote it Get detail for one provider: models, tier breakdown, price range. Args: provider_name: Provider name, e.g. 'DeepInfra', 'Novita', 'Venice'. Returns: provider detail with model list and pricing.
list_providersList all inference providers with model counts and price stats.No findings
Why it is in this group
- The name "list_providers" says "list": a word for reading.
Description, as the server wrote it List all inference providers with model counts and price stats.
search_modelsSearch and list AI inference models with current pricing.No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Search and list AI inference models with current pricing. Args: query: Text search on model id/name (optional). tier: Filter by tier: frontier | standard | budget | micro (optional). limit: Max results (1-100, default 25). sort: Sort key: blended | input | output | sit_score | sit_adjusted_price (default sit_adjusted_price). Returns: models with input/output/blended $/M pricing, provider, tier.
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, 18:57 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.inferenceindexer.ai/mcp: tools/list returned 10 tools to an anonymous client, including recommend_models (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http inferenceindexer https://api.inferenceindexer.ai/mcpclaude mcp add --transport http inferenceindexer https://api.inferenceindexer.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__inferenceindexer__explain_model",
"mcp__inferenceindexer__search_models",
"mcp__inferenceindexer__get_model",
"mcp__inferenceindexer__get_model_history",
"mcp__inferenceindexer__list_providers",
"mcp__inferenceindexer__get_provider",
"mcp__inferenceindexer__get_composite_latest",
"mcp__inferenceindexer__get_composite_history",
"mcp__inferenceindexer__compare_providers"
],
"ask": [
"mcp__inferenceindexer__recommend_models"
],
"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 inferenceindexer. 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.DesMartin01/inferenceindexer-mcp/verify?hash=94342926d19253696091f34ce10faaca30e9a956d570f5bc61eb6ac02cfe27fd" | jq -e '.changed == false'Pinned hash 94342926d192, from Nov 15, 2026, 19:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.DesMartin01/inferenceindexer-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.DesMartin01/inferenceindexer-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:15 UTC.
inferenceindexer-mcp server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the inferenceindexer-mcp server safe?
- No scan can promise that. What its definitions show: 10 tools, 1 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 inferenceindexer-mcp server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the inferenceindexer-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 inferenceindexer-mcp server have?
- 10 tools: 1 write, 9 read. recommend_models, explain_model, search_models, get_model, get_model_history, list_providers, get_provider, get_composite_latest and 2 more.
Does the inferenceindexer-mcp server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the inferenceindexer-mcp server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the inferenceindexer-mcp server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 15, 2026.