mcpbeat

Palimpsest — censorship and model-eval observatory MCP Server

io.github.beepboop2025/palimpsest
answering

Palimpsest — censorship and model-eval observatory is answering right now. Last checked 5 min ago. It exposes 4 tools. Last commit 4 Aug 2026.

Live internet-censorship signals and tamper-evident, pre-registered, hash-chained AI model evals.

Uptime history 39 hours of history
39 hours agonow
100.0%
Uptime 24h
91 of 91 checks
4
Tools
read from the server
102 ms
Response time
average over 24h
3
Stars
last commit 4 Aug 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

run in your terminal
claude mcp add palimpsest --transport http https://api.seiche.info/palimpsest/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "palimpsest": {
      "url": "https://api.seiche.info/palimpsest/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.palimpsest]
url = "https://api.seiche.info/palimpsest/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "palimpsest": {
      "url": "https://api.seiche.info/palimpsest/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "palimpsest": {
      "url": "https://api.seiche.info/palimpsest/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

gfw
gfw_reading
Read the Great Firewall's current state at both layers in one call: live network blocking measured inside China via OONI (website, messenger and circumvention-tool reachability) joined with model-layer censorship from the Generative Firewall Index over Chinese LLMs. Takes no arguments. A combined convenience view — for one layer's full raw payload use get_signal with 'ooni-gfw' or 'generative-firewall-index'.
signal
get_signal
Read the full latest published reading of one named signal: the raw payload with its generated_at timestamp, method scope and upstream sources, exactly as served on palimpsest.info. Call list_signals first to discover valid names. Use this for the AI-model-evaluation side too: 'eval-registry' returns the pre-registered, hash-chained eval ledger with its verified flag and Merkle root, and 'refusal-drift' returns the current frontier-model refusal reading on the frozen benign probe set. Distinct from gfw_reading, which merges the two Great Firewall layers into one combined view.
signals
list_signals
List every live signal Palimpsest publishes, across both of its applications: name, one-line description and source URL for each. Censorship and information control — OONI Great Firewall probes, Censored Planet, IODA outages, circumvention demand, takedown and redaction pressure, and the board's own verdict. AI model evaluation — the tamper-evident, pre-registered eval registry (hash-chained and Merkle-anchored) and frontier-model refusal drift, alongside the Generative Firewall Index over Chinese LLMs. Takes no arguments. Call this first to discover signal names, then get_signal for one full reading.
whats
whats_happening
Judge whether anything is happening in Chinese censorship right now, across every signal at once: the board's own cross-signal verdict with the multiplicity paid for (false-discovery control) and coverage confounds flagged as measurement artifacts, never findings. Takes no arguments. Use this instead of fetching signals individually and reconciling them yourself; then use get_signal to drill into whichever signal moved. Scope note: this is the censorship board. For the AI-model-evaluation side use get_signal with 'eval-registry' or 'refusal-drift'.

Endpoints

URLTransportStateLatencyChecked
https://api.seiche.info/palimpsest/mcp streamable-http answering 92 ms 5 min ago

Palimpsest — censorship and model-eval observatory — questions

Answers built from our own checks of this server.

What can Palimpsest — censorship and model-eval observatory do?
It exposes 4 tools, read directly from the server on our last check. Among them: get_signal, gfw_reading, list_signals, whats_happening. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Palimpsest — censorship and model-eval observatory working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 102 ms. The bar chart above shows every period we have measured.
How do I connect Palimpsest — censorship and model-eval observatory?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Palimpsest — censorship and model-eval observatory need an API key?
No. Palimpsest — censorship and model-eval observatory completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Palimpsest — censorship and model-eval observatory?
It answers our handshake in 102 ms on average, which is faster than 83% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Palimpsest — censorship and model-eval observatory open source?
Yes — it is published under the MIT licence, written in Python and 3 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.