Skip to content

Network Evidence MCP server

io.github.ZzNible/network-evidenceZzNiblestreamable-httpv0.0.2Scanned

Read-only offline network profiles, caller-supplied Discovery and historical/synthetic cases.

3 tools: 1 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 1 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

1 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 Network Evidence MCP server can do

The Network Evidence MCP server is published by the GitHub account ZzNible. It has 3 tools. It can create or change data (1 tool: discover_network_candidates), but cannot delete data. 2 tools only read.

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

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Last scanned Nov 2, 2026, version 0.0.2.

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.

3 tools

Changes things 1Claude Code: ask
  • discover_network_candidatesRuns the real @nec/discovery discoverNetworks (classification by @nec/core only) over 1..16 EXPLICIT, complete, already-derived candidate contexts you supply (network + ResolverMan…1 finding

    Why it is in this group

    • The description's first verb is "run": 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 "discover_network_candidates" 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 "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Runs the real @nec/discovery discoverNetworks (classification by @nec/core only) over 1..16 EXPLICIT, complete, already-derived candidate contexts you supply (network + ResolverManifest + CapabilitySnapshot in nec-wire-json-v1 form) and Core DiscoveryRequirements. Returns the Core-built, Core-verified DiscoverNetworksResult with digests and per-candidate eligible/conditional/ineligible copied from Core. The outcome depends ONLY on the supplied snapshots; this server observes nothing and does NOT choose, rank or recommend a network. Any resolver-specific evidence preflight is external to this tool. Invalid or incoherent contexts fail closed with a coded error.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Core Discovery over explicit candidate contexts
Only reads 2Show 2 read-only tools
  • get_reviewed_evidence_caseReturns ONE case by exact id (f1, f2, f3, synthetic-local-core-golden) from the shipped, checksum-pinned examples/ne-maps/data/collection.json: the browser-safe Lens envelope verba…Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "return" and "browser": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Returns ONE case by exact id (f1, f2, f3, synthetic-local-core-golden) from the shipped, checksum-pinned examples/ne-maps/data/collection.json: the browser-safe Lens envelope verbatim (all limitations, unavailable/unknown states and nonClaims preserved), its source provenance and an explicit label. f1/f2/f3 are HISTORICAL reviewed exports of past public-network observations; synthetic-local-core-golden is a SYNTHETIC fixture, not a network observation. No case is live evidence.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Read one shipped reviewed NE Maps case
  • list_network_profilesReturns the FIXED public profile inventory (Base mainnet eip155:8453, Base Sepolia eip155:84532, Solana mainnet, Solana devnet, zkSYS Tanenbaum testnet eip155:57057 replay-only) wi…No findings

    Why it is in this group

    • The name "list_network_profiles" says "list": a word for reading.
    Description, as the server wrote it
    Returns the FIXED public profile inventory (Base mainnet eip155:8453, Base Sepolia eip155:84532, Solana mainnet, Solana devnet, zkSYS Tanenbaum testnet eip155:57057 replay-only) with each resolver manifest's DECLARED capabilities and the truth boundaries. Nothing is observed: every currentSupport/currentAvailability is 'not_assessed'. Profile membership is not live availability. Takes no arguments.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List fixed Network Evidence profiles

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.

Sign-in required, no OAuth metadata

Looked at Nov 20, 2026, 19:01 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
503
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: initialize answered HTTP 503.

Posture changes

  1. Nov 20, 2026
    • HTTP status of an anonymous initialize: 500 to 503
  2. Nov 13, 2026
    • HTTP status of an anonymous initialize: 200 to 500
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "discover_network_candidates" 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 "run": a word for a change.

    What this check looks for

History

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

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 500 -> 503.View diff
    • HTTP status of an anonymous initialize: 500 to 503
  2. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 500; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 1 -> 0 (and 1 more).View diff
    • HTTP status of an anonymous initialize: 200 to 500
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 0.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http network-evidence https://network-evidence-mcp-jrkc26rjga-ew.a.run.app/mcp
claude mcp add --transport http network-evidence https://network-evidence-mcp-jrkc26rjga-ew.a.run.app/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__network-evidence__list_network_profiles",
      "mcp__network-evidence__get_reviewed_evidence_case"
    ],
    "ask": [
      "mcp__network-evidence__discover_network_candidates"
    ],
    "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 network-evidence. Review it before you use it.

Capability tags behind 1 rule
  • mcp__network-evidence__get_reviewed_evidence_case 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.ZzNible/network-evidence/verify?hash=d5e4bd7f0f438f1b7693b504987931b847f1ffa92bd2f18209d4cedd2b07aafd" | jq -e '.changed == false'

Pinned hash d5e4bd7f0f43, from Nov 2, 2026, 23:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.ZzNible/network-evidence/changes.xml

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

Badge

Anlyon Radar badge for io.github.ZzNible/network-evidence
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.ZzNible/network-evidence.svg)](https://radar.anlyon.com/servers/io.github.ZzNible/network-evidence)

Source: MCP Registry · repository. Synced Nov 14, 2026, 15:17 UTC.

Network Evidence MCP server: questions and answers

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

Is the Network Evidence MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Network Evidence MCP server delete data?

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

Can the Network Evidence 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 Network Evidence MCP server have?

3 tools: 1 write, 2 read. discover_network_candidates, list_network_profiles and get_reviewed_evidence_case.

Does the Network Evidence MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Network Evidence MCP server send data to outside services?

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

Has the Network Evidence MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 2, 2026.