Skip to content
The Quiet Internet logo

The Quiet Internet MCP server

Which MCP servers are The Quiet Internet's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to The Quiet Internet

Whose server it is
  • Registry nametop.stillglowing/wallverified in the MCP registry

The registry name sits under stillglowing.top. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools3
  • Server calls itselfstill-glowing
  • Server version1.0.0
  • Protocol version2025-11-25

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 169 ms.

Should an agent connect itNot proven either way yet
  • Its tools do Leave one anonymous thought as a trace in the field; Listen to signals other people have left behind, but not Pick a shape and glow for a released note.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "Leave one anonymous thought as a trace in the field", the likely first call is leave_trace.
  • For "Listen to signals other people have left behind", the likely first call is receive_bottle.
  • Parameters are untyped or undescribed in 1 of 3 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it2 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer538 ms
  • Space in an agent's context≈ 217 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 94 of 100
  • Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 1 of 3

What an agent can do with it

  • can do · Leave one anonymous thought as a trace in the field
  • can do · Listen to signals other people have left behind
  • cannot · Pick a shape and glow for a released note

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers3 tools · read 2026-10-26
  • describe_wall

    Explain this wall and its ethos.

  • receive_bottle

    Receive one randomly selected public trace.

  • leave_trace

    Publish one short trace. Requires explicit confirm=true and must never contain private information.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "wall": {
      "type": "http",
      "url": "https://stillglowing.top/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http stillglowing https://stillglowing.top/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://stillglowing.top/mcp as a custom connector in the settings.

OpenAPI spec

3 paths, read 2026-10-26. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.