Behavior Trees MCP server
io.github.behaviortrees/behaviortreesbehaviortreesstreamable-httpv0.2.0Scanned
Validate, convert (behavior3 JSON, BehaviorTree.CPP XML) and open behavior trees in a visual editor
6 tools: 1 do something that can't be undone, 1 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- 2 findings
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 Behavior Trees MCP server can do
The Behavior Trees MCP server is published by the GitHub account behaviortrees. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (convert_tree) and create or change data (1 tool: create_editor_link), but cannot delete data. 4 tools only read.
1 tool brings in text other people can write (read_guide); 1 tool can send data out of your system (convert_tree).
The fixed checks matched 2 findings (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 14, 2026, version 0.2.0.
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
Can't be undone 1Claude Code: ask
convert_treeConvert between behavior3 JSON and BehaviorTree.CPP XML (v4 for ROS 2 Jazzy and Groot2, v3 for ROS 2 Humble), the same way the editor imports and exports.Can send data out1 finding
Why it is in this group
- The name "convert_tree" says "convert": a word for a change.
- 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 "convert_tree" 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 name "convert_tree" says "convert": a word for a change.
Description, as the server wrote it Convert between behavior3 JSON and BehaviorTree.CPP XML (v4 for ROS 2 Jazzy and Groot2, v3 for ROS 2 Humble), the same way the editor imports and exports. Returns the converted text and any issues (BT.CPP has no equivalent for some behavior3 nodes and vice versa).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Convert a behavior tree
Changes things 1Claude Code: ask
create_editor_linkReturns a url that opens the tree in the behaviortrees.com editor in the user's browser, auto-laid-out and editable, with no account needed.1 finding
Why it is in this group
- The name "create_editor_link" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "create_editor_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_editor_link" says "create": a word for a change.
Description, as the server wrote it Returns a url that opens the tree in the behaviortrees.com editor in the user's browser, auto-laid-out and editable, with no account needed. The tree travels inside the link (the URL fragment), so nothing is uploaded or stored. Fails with the validation errors if the tree has any.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Open a tree in the editor
Only reads 4Show 4 read-only tools
get_exampleComplete, working example trees (enemy patrol, cooldown-gated attacks, robot navigation with recovery, and more) to learn the format from or start with.No findings
Why it is in this group
- The name "get_example" says "get": a word for reading.
Description, as the server wrote it Complete, working example trees (enemy patrol, cooldown-gated attacks, robot navigation with recovery, and more) to learn the format from or start with. Without an id, lists the examples; with an id, returns that tree as behavior3 JSON.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Get an example tree
list_node_typesThe built-in behavior3 nodes a tree can use without declaring them: composites (Sequence, Priority = selector/fallback, MemSequence, MemPriority), decorators (Inverter, Repeater, M…No findings
Why it is in this group
- The name "list_node_types" says "list": a word for reading.
Description, as the server wrote it The built-in behavior3 nodes a tree can use without declaring them: composites (Sequence, Priority = selector/fallback, MemSequence, MemPriority), decorators (Inverter, Repeater, MaxTime, ...) and leaves (Wait, Succeeder, Failer, ...), with descriptions and default properties.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List built-in node types
read_guidePractical guides from behaviortrees.com/learn as Markdown: what behavior trees are, node types, blackboards, debugging, structuring large trees, and behavior trees in Unity, Unreal…Reads text others writeNo findings
Why it is in this group
- The name "read_guide" says "read": 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 Practical guides from behaviortrees.com/learn as Markdown: what behavior trees are, node types, blackboards, debugging, structuring large trees, and behavior trees in Unity, Unreal, Godot, Python and robotics (BehaviorTree.CPP, ROS 2, Nav2). Without a slug, lists the guides.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Read a behavior tree guide
validate_treeChecks a behavior tree for errors: missing or dangling children, nodes with two parents, cycles, decorators with more than one child, leaves with children, unknown node names, and …No findings
Why it is in this group
- The name "validate_tree" says "validate": a word for reading.
Description, as the server wrote it Checks a behavior tree for errors: missing or dangling children, nodes with two parents, cycles, decorators with more than one child, leaves with children, unknown node names, and BehaviorTree.CPP import problems. Returns valid (true when there are no errors), the trees found, and findings at error, warning or info level.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Validate a behavior tree
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.
- Reads private data0
- 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.
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 18, 2026, 16:22 UTC, unchanged since Nov 4, 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.behaviortrees.com/mcp: tools/list returned 6 tools to an anonymous client, including convert_tree (irreversible), create_editor_link (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "create_editor_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "create_editor_link" says "create": a word for a change.
- Warnconvert_tree
The server marks "convert_tree" 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 name "convert_tree" says "convert": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools6 changed.~6 changedView diff
- Changed:convert_treeCan't be undoneinputSchemaannotations
- Changed:create_editor_linkChanges thingsdescriptioninputSchemaannotations
- Changed:get_exampleOnly readsinputSchemaannotations
- Changed:list_node_typesOnly readsinputSchemaannotations
- Changed:read_guideOnly readsinputSchemaannotations
- Changed:validate_treeOnly readsdescriptioninputSchemaannotations
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http behaviortrees https://www.behaviortrees.com/mcpclaude mcp add --transport http behaviortrees https://www.behaviortrees.com/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__behaviortrees__validate_tree",
"mcp__behaviortrees__list_node_types",
"mcp__behaviortrees__get_example",
"mcp__behaviortrees__read_guide"
],
"ask": [
"mcp__behaviortrees__create_editor_link",
"mcp__behaviortrees__convert_tree"
],
"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 behaviortrees. Review it before you use it.
Capability tags behind 2 rules
- mcp__behaviortrees__convert_tree outbound
- mcp__behaviortrees__read_guide 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.behaviortrees/behaviortrees/verify?hash=121adc2498f3d4bd419768039a3bbb63794ffc21f41e56a0be49c525a0d4255a" | jq -e '.changed == false'Pinned hash 121adc2498f3, from Nov 14, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.behaviortrees/behaviortrees/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.behaviortrees/behaviortrees)Source: MCP Registry · repository. Synced Nov 14, 2026, 17:17 UTC.
Behavior Trees MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Behavior Trees MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 2 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 Behavior Trees MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Behavior Trees MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: convert_tree.
What tools does the Behavior Trees MCP server have?
- 6 tools: 1 irreversible, 1 write, 4 read. convert_tree, create_editor_link, validate_tree, list_node_types, get_example and read_guide.
Does the Behavior Trees MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Behavior Trees 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): convert_tree.
Has the Behavior Trees MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.