Machine Relations Index MCP server
ai.machinerelations/mrimachinerelations.aistreamable-httpv1.1.3Scanned
Machine Relations Index (MRI), created by Jaxon Parrott: the sources AI engines cite, by category.
6 tools: 6 only read.
- Reads private data · 1
- Reads text others write · 1
- 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 Machine Relations Index MCP server can do
The Machine Relations Index MCP server is published by machinerelations.ai, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (mri_get_cited_sources); 1 tool brings in text other people can write (mri_get_domain).
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 3 times since Anlyon Radar first saw them.
Last scanned Nov 17, 2026, version 1.1.3.
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.
6 tools
Only reads 6Show 6 read-only tools
mri_get_categoryReturn one category's question shapes (best tools, how buyers choose, comparisons, top lists, problem-first research, is it worth it, news) and the evidence state of each: publishe…No findings
Why it is in this group
- The name "mri_get_category" says "get": a word for reading.
Description, as the server wrote it Return one category's question shapes (best tools, how buyers choose, comparisons, top lists, problem-first research, is it worth it, news) and the evidence state of each: published with rates, collecting, or not collectable.
Annotations the server declares
- title: Get an MRI category
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mri_get_cited_sourcesRanked source domains that AI answer engines cite, pooled across engines, for one category and question shape, with citation rate (share of monitored answer runs citing the domain)…Reads private dataNo findings
Why it is in this group
- The name "mri_get_cited_sources" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "database": it reads databases.
Description, as the server wrote it Ranked source domains that AI answer engines cite, pooled across engines, for one category and question shape, with citation rate (share of monitored answer runs citing the domain), rank, percentile and source role (editorial publication, vendor-owned, analyst research, community, academic/government, market database, wire distribution). This rate is not split by engine. For one engine, use mri_get_engine.
Annotations the server declares
- title: Which sources AI engines cite
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mri_get_domainFor one domain or URL, return how often AI answer engines cite it: overall citation rate, the rate on each engine (overall.byEngine: cited runs, that engine's observed runs, and wh…Reads text others writeNo findings
Why it is in this group
- The name "mri_get_domain" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it For one domain or URL, return how often AI answer engines cite it: overall citation rate, the rate on each engine (overall.byEngine: cited runs, that engine's observed runs, and whether the engine's sample clears the evidence floor), confidence tier, rank among all cited domains and within its source role, and per-category segment rates. Use to answer 'does ChatGPT cite <site>' or 'what share of Perplexity runs cite <site>'. A published byEngine row with runsCited 0 means that engine did not cite the domain. byEngine is the whole window, not a rate inside one category.
Annotations the server declares
- title: How often AI engines cite a site
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mri_get_engineRanked sources one answer engine cites, by that engine's citation rate across the whole window; an engine whose collection changed inside the window also returns collectionRegime, …No findings
Why it is in this group
- The name "mri_get_engine" says "get": a word for reading.
Description, as the server wrote it Ranked sources one answer engine cites, by that engine's citation rate across the whole window; an engine whose collection changed inside the window also returns collectionRegime, its sources since the change, which is what it cites now. Pass category to limit the list to sources with a published segment in that category; the rate stays the whole-window rate and is not a rate inside the category. Collecting categories and engines below the evidence floor withhold the ranking. Use to answer 'what sources does Perplexity cite most?' or 'which sources does Google AI Overviews cite among published <category> sources'.
Annotations the server declares
- title: Sources one answer engine cites
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mri_list_categoriesList every Machine Relations Index category (e.g.No findings
Why it is in this group
- The name "mri_list_categories" says "list": a word for reading.
Description, as the server wrote it List every Machine Relations Index category (e.g. cybersecurity, fintech, enterprise-software, ai-visibility-geo) with the question shapes that have published citation rates, plus the source-role vocabulary. Call this first to get a valid category key.
Annotations the server declares
- title: List MRI categories
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
mri_list_enginesList each answer engine with its latest-successful model metadata and historical modelPeriods (null when unavailable), the engine's observed runs and days, whether that sample clea…No findings
Why it is in this group
- The name "mri_list_engines" says "list": a word for reading.
Description, as the server wrote it List each answer engine with its latest-successful model metadata and historical modelPeriods (null when unavailable), the engine's observed runs and days, whether that sample clears the evidence floor, and the most-cited source on that engine across the whole window.
Annotations the server declares
- title: List MRI answer engines
- 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 write1
- 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
- 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.
Tools1 changed.~1 changedView diff
- Changed:mri_list_enginesOnly readsdescription
Tools4 changed.~4 changedView diff
- Changed:mri_get_cited_sourcesOnly readsinputSchema
- Changed:mri_get_engineOnly readsdescriptioninputSchema
- Changed:mri_list_categoriesOnly readsinputSchema
- Changed:mri_list_enginesOnly readsinputSchema
Tools2 added, 2 changed.+2 added~2 changedView diff
- Added:mri_get_engineOnly reads
- Added:mri_list_enginesOnly reads
- Changed:mri_get_cited_sourcesOnly readsdescription
- Changed:mri_get_domainOnly readsdescription
Install
Pinned to version 1.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http mri https://machinerelations.ai/mcpclaude mcp add --transport http mri https://machinerelations.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__mri__mri_list_categories",
"mcp__mri__mri_get_category",
"mcp__mri__mri_get_cited_sources",
"mcp__mri__mri_get_domain",
"mcp__mri__mri_list_engines",
"mcp__mri__mri_get_engine"
],
"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 mri. Review it before you use it.
Capability tags behind 2 rules
- mcp__mri__mri_get_cited_sources private-data
- mcp__mri__mri_get_domain 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/ai.machinerelations/mri/verify?hash=73b5e3773a4da222361b6b3134582ea1b287780ac711be87f98cdd265a9857fa" | jq -e '.changed == false'Pinned hash 73b5e3773a4d, from Nov 17, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.machinerelations/mri/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.machinerelations/mri)Source: MCP Registry · repository. Synced Nov 17, 2026, 07:17 UTC.
Machine Relations Index MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Machine Relations Index MCP server safe?
- No scan can promise that. What its definitions show: 6 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 Machine Relations Index MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Machine Relations Index 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 Machine Relations Index MCP server have?
- 6 tools: 6 read. mri_list_categories, mri_get_category, mri_get_cited_sources, mri_get_domain, mri_list_engines and mri_get_engine.
Does the Machine Relations Index MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Machine Relations Index MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Machine Relations Index MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 17, 2026. Every change is on this page and in its Atom feed.