CodeCraft MCP server
io.github.TanerTalas/codecraftTanerTalasstreamable-httpv0.1.0Scanned
Checks whether generated Minecraft Bedrock content will actually load. Nine read-only tools.
9 tools: 3 change things and 6 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 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 CodeCraft MCP server can do
The CodeCraft MCP server is published by the GitHub account TanerTalas. It has 9 tools. It can create or change data (3 tools: check_feasibility, validate_script and validate_python), but cannot delete data. 6 tools only read.
2 tools read private data (get_version_info and get_schema); 1 tool can send data out of your system (validate_script).
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.
Last scanned Nov 16, 2026, version 0.1.0.
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.
9 tools
Changes things 3Claude Code: ask
check_feasibilityChecks whether a user request can be built with a behavior pack and the @minecraft/server API.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 Checks whether a user request can be built with a behavior pack and the @minecraft/server API. If it is blocked, returns why, the evidence behind that rule, and a workable alternative. Call this BEFORE writing any code or JSON: input simulation, file system access and network access do not exist in the Bedrock scripting API, and those are the most commonly hallucinated APIs.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
validate_pythonValidates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the o…1 finding
Why it is in this group
- The name "validate_python" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "validate_python" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "validate_python" says "validate": a word for reading.
Description, as the server wrote it Validates a Python automation script that runs OUTSIDE the game, on three axes: Python syntax (using the real interpreter), Minecraft commands embedded in the script (against the official command index), and the shape of the /connect WebSocket message envelope. For behavior pack scripts use validate_script instead — Python does not run inside a pack. The embedded command check is the most valuable one: a command written from memory can look syntactically fine and still do nothing in the game. Only strings starting with / are treated as commands. If syntax could not be checked, syntaxChecked is false in the result; ok:true alone does not mean the syntax is valid.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
validate_scriptCompiles a behavior pack script with the real TypeScript compiler against the actual @minecraft/server type definitions for that version.Can send data out1 finding
Why it is in this group
- The name "validate_script" says "validate": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- 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.channel): what the tool writes goes there.
Findings
- Warn
The server marks "validate_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "validate_script" says "validate": a word for reading.
Description, as the server wrote it Compiles a behavior pack script with the real TypeScript compiler against the actual @minecraft/server type definitions for that version. Returns diagnostics with line, column, TS error code and message, and reports which module versions it compiled against. Catch non-existent APIs and calls removed in later versions here — Bedrock scripting APIs written from memory are the most common source of output that fails silently.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
get_schemaSummarises the schema of a Bedrock document type: required fields, valid format_version values, and the name, type and description of every field on that node.Reads private dataNo findings
Why it is in this group
- The name "get_schema" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "summarise" and "document": it reads documents.
Description, as the server wrote it Summarises the schema of a Bedrock document type: required fields, valid format_version values, and the name, type and description of every field on that node. It does not return the raw schema — that is far too large. When a node has many fields the summary narrows and says what was shortened in the truncated field; use path to descend into a child node for full detail. Call this before writing a file to learn which fields are required and what format_version must be.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_version_infoReturns which version number belongs where for this game version: min_engine_version (a three-part array), @minecraft/server module versions, the valid format_version values for ev…Reads private dataNo findings
Why it is in this group
- The name "get_version_info" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "document": it reads documents.
Description, as the server wrote it Returns which version number belongs where for this game version: min_engine_version (a three-part array), @minecraft/server module versions, the valid format_version values for every document type, and the list of recognised document types. format_version is an axis of its own and is unrelated to the game version. Call this before writing any behavior pack file.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
lookup_idTells you whether a minecraft: identifier actually exists in this version and what kind it is (block, item, entity, biome, effect, enchantment, feature, dimension, camera preset, p…No findings
Why it is in this group
- The name "lookup_id" says "lookup": a word for reading.
Description, as the server wrote it Tells you whether a minecraft: identifier actually exists in this version and what kind it is (block, item, entity, biome, effect, enchantment, feature, dimension, camera preset, particle, potion). For a block it also returns the valid block states and the values they accept. An identifier without a namespace is treated as minecraft:. Verify every identifier here before writing it — an identifier that does not exist fails silently in the game.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
review_packValidates every file of a behavior or resource pack in one call: it applies the right validator to each file (JSON schema, script compilation, command syntax) and then runs the che…No findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
Description, as the server wrote it Validates every file of a behavior or resource pack in one call: it applies the right validator to each file (JSON schema, script compilation, command syntax) and then runs the checks a schema structurally cannot do — identifier consistency, filename rules, manifest module type, texture keys, component names, Molang queries and loot/trade table paths. This is the LAST step before handing a pack to the user, and it is both faster and broader than validating each file separately.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
validate_commandValidates a single Bedrock command line against the official command index: does the command exist, does the argument count match, are the selectors and block states valid.No findings
Why it is in this group
- The name "validate_command" says "validate": a word for reading.
Description, as the server wrote it Validates a single Bedrock command line against the official command index: does the command exist, does the argument count match, are the selectors and block states valid. When no overload matches it returns the valid usages, and it tells you whether the command requires cheats. Run every command through this before giving it to the user. `execute ... run <command>` chains are resolved: the command after run is validated too, including nested execute.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
validate_jsonValidates a behavior or resource pack JSON file against the official schema and returns the JSON pointer, the violated rule and a readable message for every error.No findings
Why it is in this group
- The name "validate_json" says "validate": a word for reading.
Description, as the server wrote it Validates a behavior or resource pack JSON file against the official schema and returns the JSON pointer, the violated rule and a readable message for every error. Unexpected property names and the valid enum values are included in the message. Run every JSON file you produce through this before handing it to the user.
Annotations the server declares
- readOnlyHint: 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 untrusted-input.
- Reads private data2
- 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 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 20, 2026, 19:00 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
- 3
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://codecraft-ashy-seven.vercel.app/mcp: tools/list returned 9 tools to an anonymous client, including check_feasibility (write), validate_script (write), validate_python (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnvalidate_script
The server marks "validate_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "validate_script" says "validate": a word for reading.
- Warnvalidate_python
The server marks "validate_python" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "validate_python" says "validate": a word for reading.
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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http codecraft https://codecraft-ashy-seven.vercel.app/mcpclaude mcp add --transport http codecraft https://codecraft-ashy-seven.vercel.app/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__codecraft__get_version_info",
"mcp__codecraft__get_schema",
"mcp__codecraft__lookup_id",
"mcp__codecraft__validate_json",
"mcp__codecraft__validate_command",
"mcp__codecraft__review_pack"
],
"ask": [
"mcp__codecraft__check_feasibility",
"mcp__codecraft__validate_script",
"mcp__codecraft__validate_python"
],
"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 codecraft. Review it before you use it.
Capability tags behind 3 rules
- mcp__codecraft__get_version_info private-data
- mcp__codecraft__get_schema private-data
- mcp__codecraft__validate_script outbound
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.TanerTalas/codecraft/verify?hash=1de821dda4ecbafd848210910b684f4dd648df2be719bb142a0b5aa9c37d2397" | jq -e '.changed == false'Pinned hash 1de821dda4ec, from Nov 16, 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/io.github.TanerTalas/codecraft/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.TanerTalas/codecraft)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:21 UTC.
CodeCraft MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CodeCraft MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 3 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 CodeCraft MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CodeCraft 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 CodeCraft MCP server have?
- 9 tools: 3 write, 6 read. check_feasibility, validate_script, validate_python, get_version_info, get_schema, lookup_id, validate_json, validate_command and 1 more.
Does the CodeCraft MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CodeCraft 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): validate_script.
Has the CodeCraft MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.