Skip to content

Conduit Router — Governed MCP Routing

org.aimlds/conduit-routeraimlds.orgstreamable-httpv1.5.1Scanned

Governed MCP routing: every agent call spend-capped, metered, sealed with a verifiable receipt.

6 tools: 1 do something that can't be undone, 1 change things and 4 only read.

Tools: 0 delete, 1 irreversible, 1 write, 4 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

2 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the Conduit Router — Governed MCP Routing can do

The Conduit Router — Governed MCP Routing is published by aimlds.org, a domain the MCP Registry verified. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (route_chat) and create or change data (1 tool: verify_receipt), but cannot delete data. 4 tools only read.

1 tool brings in text other people can write (route_chat); 1 tool can send data out of your system (route_chat).

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.

Last scanned Nov 11, 2026, version 1.5.1.

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.

6 tools

Can't be undone 1Claude Code: ask
  • route_chatSend a chat completion through Conduit Router: policy-checked, budget-checked, metered, and audit-receipted.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe description's first verb is "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a chat completion through Conduit Router: policy-checked, budget-checked, metered, and audit-receipted. Uses your own stored provider keys (BYOK). Pin a model as "provider:model" or let your standing terms choose.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 1Claude Code: ask
  • verify_receiptCryptographically verify a receipt record (yours or anyone's) against the router's audit chain: the record hash must recompute and the stored record at that sequence must match.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
    Cryptographically verify a receipt record (yours or anyone's) against the router's audit chain: the record hash must recompute and the stored record at that sequence must match.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • get_policyYour key's standing terms (mandate): task profile, per-request and daily budgets, model allowlist, fallback chain, region — plus kill-switch state.No findings

    Why it is in this group

    • The name "get_policy" says "get": a word for reading.
    Description, as the server wrote it
    Your key's standing terms (mandate): task profile, per-request and daily budgets, model allowlist, fallback chain, region — plus kill-switch state.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_receiptOne of your calls' audit receipts (id like "rcpt_12") with its hash-chain proof: record hash validity, successor linkage, and the current chain head.No findings

    Why it is in this group

    • The name "get_receipt" says "get": a word for reading.
    Description, as the server wrote it
    One of your calls' audit receipts (id like "rcpt_12") with its hash-chain proof: record hash validity, successor linkage, and the current chain head.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_usageYour cumulative meter (requests, tokens, provider cost, router charge), today's spend against your daily budget, and which providers you have keys stored for.No findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.
    Description, as the server wrote it
    Your cumulative meter (requests, tokens, provider cost, router charge), today's spend against your daily budget, and which providers you have keys stored for.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_modelsThe public model catalog: every model the router can serve, with provider, free-tier flag, task profiles, and pricing source/as-of.No findings

    Why it is in this group

    • The name "list_models" says "list": a word for reading.
    Description, as the server wrote it
    The public model catalog: every model the router can serve, with provider, free-tier flag, task profiles, and pricing source/as-of.

    Annotations the server declares

    • 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.

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 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.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:22 UTC, unchanged since Nov 12, 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
https://router.pipavia.com/.well-known/oauth-protected-resource/mcp
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://router.pipavia.com/mcp: tools/list returned 6 tools to an anonymous client, including route_chat (irreversible), verify_receipt (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.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.5.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http conduit-router https://router.pipavia.com/mcp
claude mcp add --transport http conduit-router https://router.pipavia.com/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__conduit-router__list_models",
      "mcp__conduit-router__get_usage",
      "mcp__conduit-router__get_receipt",
      "mcp__conduit-router__get_policy"
    ],
    "ask": [
      "mcp__conduit-router__route_chat",
      "mcp__conduit-router__verify_receipt"
    ],
    "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 conduit-router. Review it before you use it.

Capability tags behind 1 rule
  • mcp__conduit-router__route_chat untrusted-input, 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/org.aimlds/conduit-router/verify?hash=a31b0b72868291d3f6ae8fb493444b20dd1037f0f3196110def28f0b1ad8970c" | jq -e '.changed == false'

Pinned hash a31b0b728682, from Nov 11, 2026, 23:18 UTC.

Watch

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

https://radar.anlyon.com/servers/org.aimlds/conduit-router/changes.xml

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

Badge

Anlyon Radar badge for org.aimlds/conduit-router
[![Anlyon Radar](https://radar.anlyon.com/badge/org.aimlds/conduit-router.svg)](https://radar.anlyon.com/servers/org.aimlds/conduit-router)

Source: MCP Registry · repository. Synced Nov 11, 2026, 23:18 UTC.

Conduit Router — Governed MCP Routing: questions and answers

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

Is the Conduit Router — Governed MCP Routing safe?

No scan can promise that. What its definitions show: 6 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 Conduit Router — Governed MCP Routing delete data?

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

Can the Conduit Router — Governed MCP Routing do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: route_chat.

What tools does the Conduit Router — Governed MCP Routing have?

6 tools: 1 irreversible, 1 write, 4 read. route_chat, verify_receipt, list_models, get_usage, get_receipt and get_policy.

Does the Conduit Router — Governed MCP Routing need sign-in or OAuth?

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

Does the Conduit Router — Governed MCP Routing send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): route_chat.

Has the Conduit Router — Governed MCP Routing changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.