Skip to content

Diogenes Agent Guardrails & Sandbox MCP server

io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcpstand-out-of-my-sunstreamable-httpv1.0.0Scanned

Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.

12 tools: 9 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 9 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 5 findings

Tools listed without sign-in. Remote posture

With Anlyon

9 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 Diogenes Agent Guardrails & Sandbox MCP server can do

The Diogenes Agent Guardrails & Sandbox MCP server is published by the GitHub account stand-out-of-my-sun. It has 12 tools. It can create or change data (9 tools: verify_agent_command_safety, execute_python_sandbox, audit_mcp_server_manifest, detect_mcp_schema_rugpull and 5 more), but cannot delete data. 3 tools only read.

1 tool brings in text other people can write (sanitize_tool_output_stream).

The fixed checks matched 5 findings (annotation-conflict and credentials-mention). 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 20, 2026, version 1.0.0.

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.

12 tools

Changes things 9Claude Code: ask
  • audit_mcp_server_manifestScans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions.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
    Scans an external MCP server's initial tools/list manifest to detect tool-name shadowing (read_file, bash) and hidden prompt-injection directives in descriptions. Use when vetting a newly discovered third-party MCP server before mounting it into an agent session; for comparing a previously pinned MCP baseline against a live mid-session tools/list response, use detect_mcp_schema_rugpull instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'manifest_json' ('audit_profile' defaults to 'strict'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: External MCP Server Manifest & Tool-Poisoning Security Auditor
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • audit_outbound_egress_urlStatic validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltra…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
    Static validation firewall for outbound network destination URIs against cloud metadata IP addresses (169.254.169.254), RFC 1918 private IP blocks, and query-string secret exfiltration before agent dispatch. Use when validating a user-supplied or tool-supplied URI destination before network dispatch; for auditing local shell commands or general prompts, use verify_agent_command_safety instead. Read-only edge call (32 KB, 60 RPM): accepts 'destination_uri' ('egress_policy' defaults to 'block_private_and_metadata'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Outbound Agent URL SSRF, Metadata & Secret Exfiltration Firewall
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • audit_response_factualityCross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before delivery.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
    Cross-references factual claims, numbers, and citations in a draft agent response against retrieved source passages to flag unsupported hallucinations before delivery. Use when verifying that a generated answer is 100% grounded in source evidence before returning it to the user; for scrubbing inbound tool outputs for prompt-injection and invisible Unicode, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'claim' ('context' defaults to 'standard'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Draft Agent Response Groundedness & Hallucination Auditor
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • detect_mcp_schema_rugpullComputes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering.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
    Computes structural diffs between a pinned baseline MCP tools/list snapshot and a live server response to catch mid-session description or schema tampering. Use when verifying that a connected MCP server has not mutated its tool definitions mid-session; for performing a first-time static security audit on a single MCP manifest, use audit_mcp_server_manifest instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'baseline_tools_json' ('current_tools_json' defaults to 'standard'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Mid-Session MCP tools/list Rug-Pull & Schema Mutation Detector
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • execute_python_sandboxAudits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access.1 finding

    Why it is in this group

    • The name "execute_python_sandbox" says "execute": 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 "execute_python_sandbox" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "execute_python_sandbox" says "execute": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Audits Python source code for forbidden syscalls (os, subprocess, socket, open, eval) inside an AST-governed WebAssembly sandbox with no host filesystem access. Use when executing LLM-generated Python snippets safely; for checking shell commands without executing code, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'python_script' ('timeout_profile' defaults to 'fast_1s'), supports '?demo=true' or MPP (250 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: AST-Audited Ephemeral Python Code Execution Sandbox
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • redact_sensitive_piiRedacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission.3 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.

    Findings

    • Info

      The title mentions "Credential".

      Matched text

      title: "Zero-PII & Secret Credential Redaction Engine"

      What this check looks for
    • Info

      The annotations title mentions "Credential".

      Matched text

      annotations.title: "Zero-PII & Secret Credential Redaction Engine"

      What this check looks for
    • Info

      The description mentions "credentials".

      Matched text

      description: "...when stripping personal data or secret credentials from prompts, logs, or outbound message..."

      What this check looks for
    Description, as the server wrote it
    Redacts emails, phone numbers, SSNs, credit cards, API keys, and crypto private keys from text before logging or external transmission. Use when stripping personal data or secret credentials from prompts, logs, or outbound messages; for neutralizing indirect prompt injections and invisible Unicode in inbound tool responses, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'text' ('redaction_style' defaults to 'typed_token'), supports '?demo=true' or L402 (25 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Zero-PII & Secret Credential Redaction Engine
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • sanitize_tool_output_streamSanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, and defusing indirect…Reads text others writeNo 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

    • untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Sanitizes untrusted external tool or web-scrape outputs by stripping invisible Unicode Tag characters (U+E0000), neutralizing Markdown tracking image beacons, and defusing indirect prompt overrides. Use when cleaning raw third-party tool outputs or scraped web text before inserting it into the LLM context window; for redacting personal identifiable information (emails, SSNs, keys) from outbound text, use redact_sensitive_pii instead. Read-only edge call (32 KB, 60 RPM): accepts 'raw_tool_output' (with enum defaults), uses '?demo=true' or L402 (15 sats); HTTP 400 if invalid.

    Annotations the server declares

    • title: Indirect Prompt-Injection, Invisible Unicode & Beacon Output Scrubber
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_a2a_agent_cardVerifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing.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
    Verifies a remote agent's A2A /.well-known/agent.json discovery card, checking JWS/DID signature binding, endpoint HTTPS enforcement, and capability spoofing. Use when authenticating a peer autonomous agent before delegating subtasks or exchanging payments over A2A; for auditing an MCP tool server's tools/list manifest rather than a peer agent's A2A card, use audit_mcp_server_manifest instead. Read-only edge call (32 KB, 60 RPM): accepts 'agent_card_json' ('trust_policy' defaults to 'require_https_and_did'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: A2A /.well-known/agent.json Identity & Capability Card Verifier
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • verify_agent_command_safetyEvaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration.1 finding

    Why it is in this group

    • The description's first verb is "evaluate": 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 "verify_agent_command_safety" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Evaluates untrusted agent prompts, bash commands, and tool arguments to block prompt injection, destructive shell commands, and private-key exfiltration. Use when screening a general shell command or user prompt before autonomous agent execution; for statically validating SQL database queries at the AST level, use validate_sql_query_ast instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'payload' ('action_type' defaults to 'bash_command'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Autonomous Agent Pre-Execution Command & Prompt Injection Gate
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • detect_agent_action_loopAnalyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn.No findings

    Why it is in this group

    • The description's first verb is "analyze": a word for reading.
    Description, as the server wrote it
    Analyzes an agent's recent tool-call trace to detect identical retry spins, A/B state oscillation, and runaway token burn. Use when monitoring autonomous agent execution loops to decide whether to continue or trip a token-burn breaker; for inspecting a single command payload for security threats before execution, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'action_trace_json' ('sensitivity' defaults to 'strict_2_repeats'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Autonomous Agent Action-Trace Loop & Token-Burn Circuit Breaker
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_mcp_sampling_requestAudits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quota hijacking.No findings

    Why it is in this group

    • The name "validate_mcp_sampling_request" says "validate": a word for reading.
    Description, as the server wrote it
    Audits inbound MCP sampling/createMessage callbacks from connected servers to block cross-server context snooping (includeContext='allServers') and token quota hijacking. Use when filtering a connected MCP server's request to sample the host LLM; for scrubbing text returned from a standard synchronous tools/call response, use sanitize_tool_output_stream instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sampling_request_json' ('max_tokens_ceiling' defaults to '512'), supports '?demo=true' or L402 (20 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: Inbound MCP sampling/createMessage Reverse-Injection Firewall
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • validate_sql_query_astPerforms static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses.No findings

    Why it is in this group

    • The name "validate_sql_query_ast" says "validate": a word for reading.
    Description, as the server wrote it
    Performs static AST syntax tree parsing on SQL statements to verify strictly read-only SELECT clauses and reject mutations, stacked queries, or comment bypasses. Use when verifying that an agent-authored SQL statement is strictly read-only before running it on a database; for screening non-SQL bash commands or general agent prompts, use verify_agent_command_safety instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'sql_statement' ('dialect' defaults to 'postgres'), supports '?demo=true' or L402 (15 sats), and returns HTTP 400 if invalid.

    Annotations the server declares

    • title: AST-Level Read-Only SQL Query & Injection Safety Validator
    • 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 private-data or outbound.

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 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, 19:11 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
9
Protocol version
2024-11-05
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 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails: tools/list returned 12 tools to an anonymous client, including verify_agent_command_safety (write), execute_python_sandbox (write), audit_mcp_server_manifest (write), detect_mcp_schema_rugpull (write), sanitize_tool_output_stream (write) and 4 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn3 info
  • The server marks "verify_agent_command_safety" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "evaluate": a word for a change.

    What this check looks for
  • The server marks "execute_python_sandbox" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "execute_python_sandbox" says "execute": a word for a change.

    What this check looks for
  • The title mentions "Credential".

    Matched text

    title: "Zero-PII & Secret Credential Redaction Engine"

    What this check looks for
  • The annotations title mentions "Credential".

    Matched text

    annotations.title: "Zero-PII & Secret Credential Redaction Engine"

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...when stripping personal data or secret credentials from prompts, logs, or outbound message..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools12 changed.~12 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http diogenes-agent-guardrails https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails
claude mcp add --transport http diogenes-agent-guardrails https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails

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__diogenes-agent-guardrails__validate_sql_query_ast",
      "mcp__diogenes-agent-guardrails__validate_mcp_sampling_request",
      "mcp__diogenes-agent-guardrails__detect_agent_action_loop"
    ],
    "ask": [
      "mcp__diogenes-agent-guardrails__verify_agent_command_safety",
      "mcp__diogenes-agent-guardrails__execute_python_sandbox",
      "mcp__diogenes-agent-guardrails__audit_mcp_server_manifest",
      "mcp__diogenes-agent-guardrails__detect_mcp_schema_rugpull",
      "mcp__diogenes-agent-guardrails__sanitize_tool_output_stream",
      "mcp__diogenes-agent-guardrails__redact_sensitive_pii",
      "mcp__diogenes-agent-guardrails__verify_a2a_agent_card",
      "mcp__diogenes-agent-guardrails__audit_outbound_egress_url",
      "mcp__diogenes-agent-guardrails__audit_response_factuality"
    ],
    "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 diogenes-agent-guardrails. Review it before you use it.

Capability tags behind 1 rule
  • mcp__diogenes-agent-guardrails__sanitize_tool_output_stream 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.stand-out-of-my-sun/diogenes-agent-guardrails-mcp/verify?hash=7fbf16eeb8b9e638a74fff858fa89d0bb6e71abe3d0ef6599a736b93661202d7" | jq -e '.changed == false'

Pinned hash 7fbf16eeb8b9, from Nov 20, 2026, 14:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp.svg)](https://radar.anlyon.com/servers/io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.

Diogenes Agent Guardrails & Sandbox MCP server: questions and answers

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

Is the Diogenes Agent Guardrails & Sandbox MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 9 of which can change, send or delete something, and 5 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 Diogenes Agent Guardrails & Sandbox MCP server delete data?

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

Can the Diogenes Agent Guardrails & Sandbox 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 Diogenes Agent Guardrails & Sandbox MCP server have?

12 tools: 9 write, 3 read. verify_agent_command_safety, execute_python_sandbox, audit_mcp_server_manifest, detect_mcp_schema_rugpull, sanitize_tool_output_stream, redact_sensitive_pii, verify_a2a_agent_card, audit_outbound_egress_url and 4 more.

Does the Diogenes Agent Guardrails & Sandbox MCP server need sign-in or OAuth?

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

Does the Diogenes Agent Guardrails & Sandbox MCP server send data to outside services?

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

Has the Diogenes Agent Guardrails & Sandbox MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.