RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
Diogenes Agent Guardrails & Sandbox is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
80/100
tool-list score
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http diogenes-agent-guardrails-sandbox-mcp https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrails
# 2 — ask your agent for something these tools do
# verify_agent_command_safety, validate_sql_query_ast, execute_python_sandbox and 9 more
Diogenes Agent Guardrails & Sandbox costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SOAll 6 servers
stand-out-of-my-sun6 servers
4 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http diogenes-agent-guardrails-sandbox-mcp https://diogenes-micro-gateway.corinth.workers.dev/mcp/agent-guardrailsReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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): a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| payload | string | yes | Raw command string, script snippet, or untrusted prompt to inspect for safety violations. |
| action_type | string | no | Execution context of the payload; defaults to 'bash_command' when omitted. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql_statement | string | yes | SQL statement string to statically parse and audit for read-only SELECT compliance (e.g. 'SELECT id, email FROM users WHERE active = 1'). |
| dialect | string | no | SQL dialect ruleset used for AST token inspection; defaults to 'postgres' when omitted. |
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_prof
| Parameter | Type | Required | Notes |
|---|---|---|---|
| python_script | string | yes | Python 3 source script to audit and execute strictly inside an isolated AST-governed, non-privileged WebAssembly sandbox with no host filesystem access. |
| timeout_profile | string | no | Execution resource ceiling; defaults to 'standard_5s' when omitted. |
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. St
| Parameter | Type | Required | Notes |
|---|---|---|---|
| manifest_json | string | yes | JSON string or object containing the external MCP server's tools array to audit. |
| audit_profile | string | no | Sensitivity level for flagging system-tool name shadowing; defaults to 'strict' when omitted. |
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 (
| Parameter | Type | Required | Notes |
|---|---|---|---|
| baseline_tools_json | string | yes | JSON-serialized baseline tools/list array captured when the MCP server was first trusted. |
| current_tools_json | string | no | JSON-serialized live tools/list array to compare against the baseline; defaults to '[]' when omitted. |
| diff_mode | string | no | Comparison strictness across descriptions and inputSchema; defaults to 'full_structural' when omitted. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sampling_request_json | string | yes | JSON string or object representing the inbound MCP sampling/createMessage payload. |
| max_tokens_ceiling | string | no | Maximum completion token quota allowed for server callbacks; defaults to '2048' when omitted. |
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 te
| Parameter | Type | Required | Notes |
|---|---|---|---|
| raw_tool_output | string | yes | Untrusted text returned by an external tool, webhook, or web scraper. |
| wrap_tag | string | no | XML isolation wrapper applied around the sanitized text; defaults to 'tool_data' when omitted. |
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 (ma
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Input text containing potential PII or secret keys to redact. |
| redaction_style | string | no | Placeholder format used for redacted spans; defaults to 'typed_token' when omitted. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action_trace_json | string | yes | JSON-serialized array of recent agent actions (e.g. '[{"tool":"search","status":"err"}]'). |
| sensitivity | string | no | Cycle detection threshold; defaults to 'standard_3_repeats' when omitted. |
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. Rea
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_card_json | string | yes | JSON string or object of the peer agent's /.well-known/agent.json descriptor. |
| trust_policy | string | no | Verification policy for DID/DNS binding; defaults to 'require_https_and_did' when omitted. |
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. Rea
| Parameter | Type | Required | Notes |
|---|---|---|---|
| destination_uri | string | yes | Outbound HTTP/HTTPS destination URI to inspect before fetching (e.g. 'https://api.example.com/v1/webhook'). |
| egress_policy | string | no | Network egress policy; defaults to 'block_private_and_metadata' when omitted. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| claim | string | yes | Draft agent response or factual statement to verify for hallucinations. |
| context | string | yes | Authoritative source text or retrieved RAG passages that the claim must be grounded in. |
| strictness | string | no | Entailment threshold required for numbers and dates; defaults to 'exact_entailment' when omitted. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Diogenes Agent Guardrails & Sandbox or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
BTool-list grade · score 80 / 100
Release 1.0.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score80
Findings1 threat · 3 capability
Capabilitycritical
Coveragemanifest
Verificationnot in this report
Surface digest19c7464be32eef4aaf312d6d92da81a2619283e5c30080faac62b2c2e691440f
Score vectorthreat 94 → client 80
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| verify_agent_command_safety | no tags | |
| validate_sql_query_ast | sensitive-source | sensitive-source: keyword "sql_query", parameter "sql" |
| execute_python_sandbox | code-exec | code-exec: parameter "script" |
| audit_mcp_server_manifest | sensitive-source | sensitive-source: keyword "read_file" |
| detect_mcp_schema_rugpull | no tags | |
| validate_mcp_sampling_request | no tags | |
| sanitize_tool_output_stream | untrusted-input | untrusted-input: keyword "scrape" |
| redact_sensitive_pii | no tags | |
| detect_agent_action_loop | no tags | |
| verify_a2a_agent_card | no tags | |
| audit_outbound_egress_url | no tags | |
| audit_response_factuality | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
sanitize_tool_output_stream → audit_mcp_server_manifest → execute_python_sandbox
A cross-tool exfiltration chain exists: sanitize_tool_output_stream → audit_mcp_server_manifest → execute_python_sandbox.
Supply chain and provenance
Integrityfirst-seen
Surface digest19c7464be32eef4a
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Diogenes Agent Guardrails & Sandbox can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.