Equation.io MCP server
io.equation/equationequation.iostreamable-httpv1.0.1Scanned
Create interactive 2D and 3D graphs with validated equations, shareable links, and PNG previews.
3 tools: 2 change things and 1 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 1
- 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 Equation.io MCP server can do
The Equation.io MCP server is published by equation.io, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: encode_graph_url and decode_graph_url), but cannot delete data. 1 tool only reads.
1 tool reads private data (show_graph); 1 tool brings in text other people can write (show_graph); 1 tool can send data out of your system (decode_graph_url). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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 11, 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.
3 tools
Changes things 2Claude Code: ask
decode_graph_urlDecode an equation.io link (either the #-fragment form or the /g/ share form) into its list of equation rows, so you can edit them and build a new link with encode_graph_url.Can send data outNo 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
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Decode an equation.io link (either the #-fragment form or the /g/ share form) into its list of equation rows, so you can edit them and build a new link with encode_graph_url. The rows use the equation.io syntax documented in the "syntax" MCP resource (also at https://equation.io/llms.txt).
Annotations the server declares
- title: Read a graph link
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
encode_graph_urlBuild an equation.io graph link, validating every row with the app's parser.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 Build an equation.io graph link, validating every row with the app's parser. Pass the COMPLETE graph in "equations": a flat array of strings, one equation or definition per string, in display order — when editing an existing graph (see decode_graph_url), include unchanged rows too. Rows can be: equations and inequalities in x,y (curves, regions; z makes it 3D), bare expressions in x, y (scalar fields — a curve is written y = f(x); complex plots via w), points (rows report "draggable"), parametric tuples in u,v — and definitions: "a = 2" (a draggable slider), "f(x) = x^3 - a x", coordinate fields like "r = sqrt(x^2+y^2)" for polar. t animates. Also derivatives d/dx, integrals int[a..b] f dx, sums sum[n=1..N], domain()/conformal()/iter() for complex plots, rgb()/hsl()/oklch() color fields, y' = … slope fields, random variables "X ~ Normal(m, s)"/"P(0<X<2)"/"E(X^2)", and "view(x = -5..5, y = -2..2)"/"camera(theta, phi)" framing rows. That is a menu, not the syntax: before your first non-trivial graph, read the "syntax" MCP resource (also at https://equation.io/llms.txt). The result returns text and structured data only. "rows" gives each equation's validation result: status "ok" with its kind, or "error" with the parser message. The link is usable only once every row is "ok". Give users the share_url (it unfurls to a link card in chat apps); url is the equivalent #-fragment form. No image is attached to the tool response.
Annotations the server declares
- title: Create a graph link
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: true
Only reads 1Show 1 read-only tool
show_graphDisplay an interactive equation.io graph inside the conversation, with editable equations, sliders, pan/zoom, and 3D rotation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "show_graph" says "show": a word for reading.
What it can reach
- private-dataThe description's first sentence says "display" and "conversation": it reads messages.
- untrusted-inputThe description's first sentence says "display" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Display an interactive equation.io graph inside the conversation, with editable equations, sliders, pan/zoom, and 3D rotation. Use when the user asks to see or explore a graph. Pass the COMPLETE graph as "equations", one equation or definition per string, preserving unchanged rows when editing. For a slider use "a = 2" then "y = a sin(x)". For advanced syntax read the "syntax" resource (https://equation.io/llms.txt). Returns per-row validation and share links; a row with status "error" is not drawn until its text is corrected and the graph resubmitted. Use encode_graph_url for validation or link-only requests (including share-link preview notes). In clients without UI support, provide share_url.
Annotations the server declares
- title: Show an interactive graph
- readOnlyHint: true
- openWorldHint: false
- destructiveHint: false
- idempotentHint: 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.
1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__equation__decode_graph_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, 18:55 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://equation.io/mcp: tools/list returned 3 tools to an anonymous client, including encode_graph_url (write), decode_graph_url (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 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http equation https://equation.io/mcpclaude mcp add --transport http equation https://equation.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__equation__show_graph"
],
"ask": [
"mcp__equation__encode_graph_url",
"mcp__equation__decode_graph_url"
],
"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 equation. Review it before you use it.
Capability tags behind 2 rules
- mcp__equation__decode_graph_url outbound
- mcp__equation__show_graph private-data, 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.equation/equation/verify?hash=0d635666b7a5b6d3f1ad3d3311e19492da4a0ec18c421f07e3127d376a679fda" | jq -e '.changed == false'Pinned hash 0d635666b7a5, from Nov 11, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.equation/equation/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.equation/equation)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:13 UTC.
Equation.io MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Equation.io MCP server safe?
- No scan can promise that. What its definitions show: 3 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 Equation.io MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Equation.io 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 Equation.io MCP server have?
- 3 tools: 2 write, 1 read. encode_graph_url, decode_graph_url and show_graph.
Does the Equation.io MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Equation.io 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): decode_graph_url.
Has the Equation.io MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.