Skip to content

Cyphrex MCP server

io.github.getcyphrex/cyphrex-mcpgetcyphrexstreamable-httpv0.3.0Scanned

Checks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.

11 tools: 7 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 7 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

7 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 Cyphrex MCP server can do

The Cyphrex MCP server is published by the GitHub account getcyphrex. It has 11 tools. It can create or change data (7 tools: register_agent, check_action, set_behavior_profile, scan_mcp_tool_result and 3 more), but cannot delete data. 4 tools only read.

None of its tools reads private data, brings in text other people write, or sends data 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, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 11, 2026, version 0.3.0.

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.

11 tools

Changes things 7Claude Code: ask
  • check_actionRun Cyphrex check on a proposed actionNo findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    Description, as the server wrote it
    Run Cyphrex check on a proposed action
  • proxy_mcp_requestProxy a JSON-RPC tools/list or tools/call request to an upstream MCP server.No findings

    Why it is in this group

    • The name "proxy_mcp_request" says "request": a word for a change.
    Description, as the server wrote it
    Proxy a JSON-RPC tools/list or tools/call request to an upstream MCP server. Cyphrex enforces threat policy before the caller receives the upstream result.
  • register_agentRegister a new Cyphrex agentNo 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
    Register a new Cyphrex agent
  • run_aiuc1_gap_checkPublic AIUC-1 readiness self-check.No findings

    Why it is in this group

    • The name "run_aiuc1_gap_check" says "run": a word for a change.
    Description, as the server wrote it
    Public AIUC-1 readiness self-check. No API key. AIUC-1 readiness self-check. Not certification, and not affiliated with or endorsed by AIUC.
  • scan_mcp_tool_resultScan an upstream MCP tools/call result for PII, injection, and volume anomaliesNo 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
    Scan an upstream MCP tools/call result for PII, injection, and volume anomalies
  • set_behavior_profileSet behavior profile for an agentNo findings

    Why it is in this group

    • The name "set_behavior_profile" says "set": a word for a change.
    Description, as the server wrote it
    Set behavior profile for an agent
  • verify_recordCheck a record or export bundle.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
    Check a record or export bundle. Reports the signature, a public timestamp when one is present, and an RFC 3161 timestamp valid when a token is attached. A record also reports its hash chain. A bundle reports file_hashes against the manifest. Each part is pass, fail, not_present, or not_checked. A signature that verifies only with a caller-supplied key that is not Cyphrex's is pass_supplied_key. No API key.
Only reads 4Show 4 read-only tools
  • get_audit_logGet Cyphrex audit log for an agentNo findings

    Why it is in this group

    • The name "get_audit_log" says "get": a word for reading.
    Description, as the server wrote it
    Get Cyphrex audit log for an agent
  • log_actionLog an executed action for a Cyphrex agentNo findings

    Why it is in this group

    • The name "log_action" says "log": a word for reading.
    Description, as the server wrote it
    Log an executed action for a Cyphrex agent
  • scan_mcp_tools_listScan an upstream MCP tools/list payload for threats and diff tool snapshotsNo findings

    Why it is in this group

    • The name "scan_mcp_tools_list" says "list": a word for reading.
    Description, as the server wrote it
    Scan an upstream MCP tools/list payload for threats and diff tool snapshots
  • verify_agentFetch/verify agent detailsNo findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.
    Description, as the server wrote it
    Fetch/verify agent details

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 untrusted-input or outbound.

Reads private data0
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, 19:05 UTC, unchanged since Oct 29, 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
7
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 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.cyphrex.io/mcp: tools/list returned 11 tools to an anonymous client, including register_agent (write), check_action (write), set_behavior_profile (write), scan_mcp_tool_result (write), proxy_mcp_request (write) and 2 more

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 5 to 7

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. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 7.View diff
    • Tools that change things, listed without credentials: 5 to 7
  2. Tools2 added.+2 addedView diff

Install

Pinned to version 0.3.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http cyphrex https://mcp.cyphrex.io/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http cyphrex https://mcp.cyphrex.io/mcp --header 'Authorization: <your-authorization>'

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__cyphrex__log_action",
      "mcp__cyphrex__get_audit_log",
      "mcp__cyphrex__verify_agent",
      "mcp__cyphrex__scan_mcp_tools_list"
    ],
    "ask": [
      "mcp__cyphrex__register_agent",
      "mcp__cyphrex__check_action",
      "mcp__cyphrex__set_behavior_profile",
      "mcp__cyphrex__scan_mcp_tool_result",
      "mcp__cyphrex__proxy_mcp_request",
      "mcp__cyphrex__run_aiuc1_gap_check",
      "mcp__cyphrex__verify_record"
    ],
    "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 cyphrex. Review it before you use it.

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.getcyphrex/cyphrex-mcp/verify?hash=4f75188dc4841fbd18990db41c59f081ffae779353163688f2c81e86c7a31125" | jq -e '.changed == false'

Pinned hash 4f75188dc484, from Nov 11, 2026, 08:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.getcyphrex/cyphrex-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.getcyphrex/cyphrex-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.getcyphrex/cyphrex-mcp.svg)](https://radar.anlyon.com/servers/io.github.getcyphrex/cyphrex-mcp)

Source: MCP Registry · repository. Synced Oct 29, 2026, 20:17 UTC.

Cyphrex MCP server: questions and answers

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

Is the Cyphrex MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 7 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 Cyphrex MCP server delete data?

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

Can the Cyphrex 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 Cyphrex MCP server have?

11 tools: 7 write, 4 read. register_agent, check_action, set_behavior_profile, scan_mcp_tool_result, proxy_mcp_request, run_aiuc1_gap_check, verify_record, log_action and 3 more.

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

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

Does the Cyphrex MCP server send data to outside services?

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

Has the Cyphrex MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.