Skip to content

protogrid MCP server

dev.protogrid/registryprotogrid.devstreamable-httpv0.1.0Scanned

Find MCP servers by intent and get exactly how to connect to them right now. No proxying.

6 tools: 2 change things and 4 only read.

Tools: 0 delete, 0 irreversible, 2 write, 4 read.
  • Reads private data · 1
  • Reads text others write · 1
  • Can send data out · 1
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 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 protogrid MCP server can do

The protogrid MCP server is published by protogrid.dev, a domain the MCP Registry verified. It has 6 tools. It can create or change data (2 tools: gate and check_server), but cannot delete data. 4 tools only read.

1 tool reads private data (get_connection); 1 tool brings in text other people can write (check_server); 1 tool can send data out of your system (check_server). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 2 findings (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 15, 2026, version 0.1.0.

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.

6 tools

Changes things 2Claude Code: ask
  • check_serverProbe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories.Reads text others writeCan send data out2 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "Probe a remote MCP server URL once, credential-free and without calling its tools, and..."

      What this check looks for
    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...ps://mcp.example.com/mcp. Never include credentials."

      What this check looks for
    Description, as the server wrote it
    Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.

    Annotations the server declares

    • title: Check an MCP server URL
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • gatePass or fail for one server against the rules you name (at least one), with every rule it broke: minimum quality or trust, checks that must not fail (e.g.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
    Pass or fail for one server against the rules you name (at least one), with every rule it broke: minimum quality or trust, checks that must not fail (e.g. tools.hidden_text), quality or trust flags that must be absent, allowed connection classes, a verified owner. A blocked or deleted listing never passes. Call it before connecting.

    Annotations the server declares

    • title: Gate a server against your rules
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 4Show 4 read-only tools
  • get_connectionMinimal connection block for the preferred remote (or package) with ${SECRET} placeholders, formatted for a target client.Reads private dataNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "secret": it reads secrets.
    Description, as the server wrote it
    Minimal connection block for the preferred remote (or package) with ${SECRET} placeholders, formatted for a target client. Secrets are never accepted or returned.

    Annotations the server declares

    • title: Get a connection block
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_serverOfficial server.json plus connectability (class, remotes with auth/health, packages), current tools, trust breakdown and identity for one server name.No findings

    Why it is in this group

    • The name "get_server" says "get": a word for reading.
    Description, as the server wrote it
    Official server.json plus connectability (class, remotes with auth/health, packages), current tools, trust breakdown and identity for one server name.

    Annotations the server declares

    • title: Get a server descriptor
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_toolsEvery current tool of a server with full input/output schemas, paginated by tool name.No findings

    Why it is in this group

    • The name "list_tools" says "list": a word for reading.
    Description, as the server wrote it
    Every current tool of a server with full input/output schemas, paginated by tool name.

    Annotations the server declares

    • title: List a server's tools
    • 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.

1 path in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__registry__check_server"
    ]
  }
}

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, 18:52 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
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
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.protogrid.dev/mcp: tools/list returned 6 tools to an anonymous client, including gate (write), check_server (write)

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 1 to 2

Findings

Matches of fixed checks, with the text they matched.

2 info
  • The description mentions "credential".

    Matched text

    description: "Probe a remote MCP server URL once, credential-free and without calling its tools, and..."

    What this check looks for
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...ps://mcp.example.com/mcp. Never include credentials."

    What this check looks for

History

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

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
    • Tools that change things, listed without credentials: 1 to 2
  2. Tools1 added, 1 changed.+1 added~1 changedView diff
    • Added:gateChanges things
    • Changed:searchOnly readsinputSchema

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http registry https://api.protogrid.dev/mcp
claude mcp add --transport http registry https://api.protogrid.dev/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__registry__search",
      "mcp__registry__get_server",
      "mcp__registry__list_tools",
      "mcp__registry__get_connection"
    ],
    "ask": [
      "mcp__registry__gate",
      "mcp__registry__check_server"
    ],
    "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 registry. Review it before you use it.

Capability tags behind 2 rules
  • mcp__registry__get_connection private-data
  • mcp__registry__check_server 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/dev.protogrid/registry/verify?hash=94c3cfb273df3317338331165993ff52624aedd7ee78a3269e95d968cee9701f" | jq -e '.changed == false'

Pinned hash 94c3cfb273df, from Nov 15, 2026, 03:18 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.protogrid/registry/changes.xml

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

Badge

Anlyon Radar badge for dev.protogrid/registry
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.protogrid/registry.svg)](https://radar.anlyon.com/servers/dev.protogrid/registry)

Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.

protogrid MCP server: questions and answers

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

Is the protogrid MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 2 of which can change, send or delete something, and 2 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 protogrid MCP server delete data?

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

Can the protogrid 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 protogrid MCP server have?

6 tools: 2 write, 4 read. gate, check_server, search, get_server, list_tools and get_connection.

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

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

Does the protogrid MCP server send data to outside services?

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

Has the protogrid MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.