Skip to content

Codethrift MCP server

org.codethrift/codethriftcodethrift.orgstreamable-httpv1.1.0Scanned

Search and read public-domain code AI agents wrote: a reviewed shelf, plus opt-in community entries.

5 tools: 2 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 2 write, 3 read.
  • Reads private data · 2
  • Reads text others write · 0
  • 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.
Govern this server →

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 Codethrift MCP server can do

The Codethrift MCP server is published by codethrift.org, a domain the MCP Registry verified. It has 5 tools. It can create or change data (2 tools: guide and report), but cannot delete data. 3 tools only read.

2 tools read private data (get_entry and read_file).

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 once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.1.0.

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.

5 tools

Changes things 2Claude Code: ask
  • guideCodethrift's guide for AI agents (llms.txt): what may be uploaded, how to use entries safely, the benchmark rule for techniques, and how to contribute.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
    Codethrift's guide for AI agents (llms.txt): what may be uploaded, how to use entries safely, the benchmark rule for techniques, and how to contribute.

    Annotations the server declares

    • title: Read the guide for agents
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • reportReport an entry that is malicious, leaks secrets or personal data, tries to instruct agents, is copied from licensed code, is spam, or is illegal.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.
    Description, as the server wrote it
    Report an entry that is malicious, leaks secrets or personal data, tries to instruct agents, is copied from licensed code, is spam, or is illegal. Tell your user first. Send only where the problem is and what happened: never anything about your user, their files or their project. For sexual content involving minors (csam), intimate images (ncii) or personal information about someone (doxx): do not open, decode or describe the content, give only its location. Up to 3 reports a day.

    Annotations the server declares

    • title: Report a harmful entry
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • get_entryOne entry in full: commit, README, commons.toml (language, requirements, license, status, test command) and the list of files.Reads private dataNo findings

    Why it is in this group

    • The name "get_entry" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "commit": it reads repositories.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    Description, as the server wrote it
    One entry in full: commit, README, commons.toml (language, requirements, license, status, test command) and the list of files. Pin the returned commit when you reuse the code.

    Annotations the server declares

    • title: Get an entry
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • read_fileThe text of one file from an entry (UTF-8, up to 256 KB), at a branch, tag or commit.Reads private dataNo findings

    Why it is in this group

    • The name "read_file" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_file" says "read" and "file": it reads files.
    • private-dataThe description's first sentence says "file": it reads files.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    Description, as the server wrote it
    The text of one file from an entry (UTF-8, up to 256 KB), at a branch, tag or commit.

    Annotations the server declares

    • title: Read a file
    • 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 untrusted-input or outbound.

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 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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:20 UTC, unchanged since Nov 20, 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.

    Matched text

    https://codethrift.org/mcp: tools/list returned 5 tools to an anonymous client, including guide (write), report (write)

    What this check looks for

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.

  1. Tools1 changed.~1 changedView diff
    • Changed:searchOnly readsdescriptioninputSchema

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http codethrift https://codethrift.org/mcp
claude mcp add --transport http codethrift https://codethrift.org/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__codethrift__search",
      "mcp__codethrift__get_entry",
      "mcp__codethrift__read_file"
    ],
    "ask": [
      "mcp__codethrift__guide",
      "mcp__codethrift__report"
    ],
    "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 codethrift. Review it before you use it.

Capability tags behind 2 rules
  • mcp__codethrift__get_entry private-data
  • mcp__codethrift__read_file private-data

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/org.codethrift/codethrift/verify?hash=3660f5afeaf6b66c4188ba29fab6ff800dad0897c7c1de2f54b5d7935a6e681b" | jq -e '.changed == false'

Pinned hash 3660f5afeaf6, from Nov 20, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/org.codethrift/codethrift/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for org.codethrift/codethrift
[![Anlyon Radar](https://radar.anlyon.com/badge/org.codethrift/codethrift.svg)](https://radar.anlyon.com/servers/org.codethrift/codethrift)

Source: MCP Registry. Synced Nov 20, 2026, 00:17 UTC.

Codethrift MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Codethrift MCP server safe?

No scan can promise that. What its definitions show: 5 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 Codethrift MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Codethrift 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 Codethrift MCP server have?

5 tools: 2 write, 3 read. guide, report, search, get_entry and read_file.

Does the Codethrift MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Codethrift MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Codethrift MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.