OpenNodes MCP server
io.github.opennodes-io/opennodesopennodes-iostreamable-httpv0.1.14Scanned
Discover verified AI inference nodes, get the best node+model per task, pre-price chains.
7 tools: 2 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- No findings
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 OpenNodes MCP server can do
The OpenNodes MCP server is published by the GitHub account opennodes-io. It has 7 tools. It can create or change data (2 tools: recommend and estimate), but cannot delete data. 5 tools only read.
7 tools bring in text other people can write (recommend, search_offerings, get_offering and 4 more).
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 8, 2026, version 0.1.14.
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
estimatePre-price an invocation chain BEFORE spending money.Reads text others writeNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Pre-price an invocation chain BEFORE spending money. Each step is either a concrete offering ("node_id/offering_id") or a `select` query that picks the best match, plus expected input and output tokens. Returns per-step cost bounds in USD, the pinned card_revision that makes each estimate enforceable at invocation, and chain totals. Use it to compare routes or budget a multi-model pipeline; nothing is invoked or charged.
Annotations the server declares
- title: Estimate the cost of a chain
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
recommendRecommend the best AI node + model for a task, with an enforceable cost estimate and human-readable reasons.Reads text others writeNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Recommend the best AI node + model for a task, with an enforceable cost estimate and human-readable reasons. Use this first when you know the task but not the model. Pass `task` (sent to this registry, which extracts features and discards the text) or `features` already extracted on your side with extractFeatures from @opennodes/core, which keeps the prompt private. Returns ranked candidates with score components, a cost estimate pinned to the node's card revision, an optional cheaper two-step scenario, and MCP tool categories the task likely needs. To browse instead, use search_offerings; to price a specific chain, use estimate.
Annotations the server declares
- title: Recommend a node and model
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
Only reads 5Show 5 read-only tools
find_locationsWhere AI models are served, by country: every known serving site (provider, region, city or facility, live or planned) with its evidence basis (claimed, documented, measured, attes…Reads text others writeNo findings
Why it is in this group
- The name "find_locations" says "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Where AI models are served, by country: every known serving site (provider, region, city or facility, live or planned) with its evidence basis (claimed, documented, measured, attested), its source page, a map point (`geo`: lat, lon, precision; `derived` when only the region is known), and the models it serves. Sites whose provider publishes no model list are included with a note. Built from node cards, imported catalogs and curated location seeds. Use it to answer "which providers serve which models in Canada" or "what serves gpt-oss within 500 km of Montréal", or to check a residency requirement before choosing an offering; then search_offerings with `region` to pick one.
Annotations the server declares
- title: Find where models run
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
find_residencyWhat each AI provider officially promises about where prompts, outputs and stored data stay: per provider (cloud, lab API, inference host or router), its commitments, each with a c…Reads text others writeNo findings
Why it is in this group
- The name "find_residency" says "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it What each AI provider officially promises about where prompts, outputs and stored data stay: per provider (cloud, lab API, inference host or router), its commitments, each with a commitment level (processing: inference and stored data stay in the scope; storage: data at rest only; none; unstated), the region codes it covers, who gets it (default, opt_in, enterprise), the programme name, a short statement and the source page with the date it was checked. Includes routers and providers with no known sites. Use it to answer "which providers keep data in the EU by default" before choosing an offering; then find_locations or search_offerings with `region`.
Annotations the server declares
- title: Find residency commitments
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
get_nodeWho runs a node and how it has behaved: operator, country and regions, endpoints, declared hardware, trust tier and its history (verifications, suspensions, reinstatements, with re…Reads text others writeNo findings
Why it is in this group
- The name "get_node" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Who runs a node and how it has behaved: operator, country and regions, endpoints, declared hardware, trust tier and its history (verifications, suspensions, reinstatements, with reasons), recent registry probe results with an availability summary, and its offerings with context window and price. Use it to vet a provider before relying on it; take node_id from search_offerings, recommend or get_offering results. For one offering's full card, use get_offering.
Annotations the server declares
- title: Get one node
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
get_offeringFull detail for one offering: endpoints, pricing, serving capabilities (context window, supported features, languages, hardware), data policy, trust tier, and the registry's observ…Reads text others writeNo findings
Why it is in this group
- The name "get_offering" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Full detail for one offering: endpoints, pricing, serving capabilities (context window, supported features, languages, hardware), data policy, trust tier, and the registry's observed probe results. Take node_id and offering_id from search_offerings or recommend results.
Annotations the server declares
- title: Get one offering
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
search_offeringsSearch AI inference offerings in the OpenNodes registry — registered nodes AND imported catalogs (OpenRouter, Hugging Face Inference Providers, models.dev, local nodes).Reads text others writeNo findings
Why it is in this group
- The name "search_offerings" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search AI inference offerings in the OpenNodes registry — registered nodes AND imported catalogs (OpenRouter, Hugging Face Inference Providers, models.dev, local nodes). All filters are optional and combine with AND. Returns { offerings, total, counts }: each offering has node_id, offering_id, model, pricing (USD per MTok), trust tier, serving capabilities, measured probe results, and a rank explanation. Use get_offering for one offering's full card, recommend to let the advisor choose.
Annotations the server declares
- title: Search inference offerings
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: true
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 outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- 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, 19:09 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
- 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://registry.opennodes.io/mcp: tools/list returned 7 tools to an anonymous client, including recommend (write), estimate (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 added, 3 changed.+2 added~3 changedView diff
- Added:find_locationsOnly reads
- Added:find_residencyOnly reads
- Changed:estimateChanges thingsinputSchema
- Changed:recommendChanges thingsinputSchema
- Changed:search_offeringsOnly readsdescriptioninputSchema
Tools2 changed.~2 changedView diff
- Changed:estimateChanges thingsinputSchema
- Changed:search_offeringsOnly readsinputSchema
Tools3 changed.~3 changedView diff
- Changed:estimateChanges thingsinputSchema
- Changed:recommendChanges thingsinputSchema
- Changed:search_offeringsOnly readsinputSchema
Install
Pinned to version 0.1.14. Values in angle brackets are yours to fill in.
claude mcp add --transport http opennodes https://registry.opennodes.io/mcpclaude mcp add --transport http opennodes https://registry.opennodes.io/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__opennodes__search_offerings",
"mcp__opennodes__get_offering",
"mcp__opennodes__get_node",
"mcp__opennodes__find_locations",
"mcp__opennodes__find_residency"
],
"ask": [
"mcp__opennodes__recommend",
"mcp__opennodes__estimate"
],
"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 opennodes. Review it before you use it.
Capability tags behind 7 rules
- mcp__opennodes__recommend untrusted-input
- mcp__opennodes__search_offerings untrusted-input
- mcp__opennodes__get_offering untrusted-input
- mcp__opennodes__get_node untrusted-input
- mcp__opennodes__estimate untrusted-input
- mcp__opennodes__find_locations untrusted-input
- mcp__opennodes__find_residency 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.opennodes-io/opennodes/verify?hash=a6234145add06a7088a4e255e928f43dd7985444fcd1fb2135d7564118465dcc" | jq -e '.changed == false'Pinned hash a6234145add0, from Nov 8, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.opennodes-io/opennodes/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.opennodes-io/opennodes)Source: MCP Registry · repository. Synced Oct 23, 2026, 14:20 UTC.
OpenNodes MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OpenNodes MCP server safe?
- No scan can promise that. What its definitions show: 7 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 OpenNodes MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OpenNodes 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 OpenNodes MCP server have?
- 7 tools: 2 write, 5 read. recommend, estimate, search_offerings, get_offering, get_node, find_locations and find_residency.
Does the OpenNodes MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OpenNodes MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the OpenNodes MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.