mcp server

Palimpsest — censorship and model-eval observatory

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

Description as published by the maintainer. Source

• version 1.3.1
• active
• evaluation

active — Most recent push to the repository was 2026-08-06. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

get_newsroom(view, limit, status, priority)

Read one evidence-first reporting surface without scraping a page or guessing a filename. Views: 'newsroom' for prioritized deterministic stories, 'wire' for normalized source dossiers, 'economy' for the revision-safe China economic pulse, 'machine-analysis' for deterministic AnalysisReports and AbstentionReports, 'investigations' for review-gated research leads, and 'editorial-readiness' for publication gates. Availability never implies publication readiness: statuses, gates, counterevidence, limitations and right-to-reply state stay attached.

get_signal(name, max_rows)

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. Required: name.

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'.

list_signals

List every published signal Palimpsest exposes, 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_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'.

Last successful function declaration observed on 2026-08-13. Source: https://api.seiche.info/palimpsest/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://api.seiche.info/palimpsest/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/beepboop2025/palimpsest
• Website — https://palimpsest.info
• Remote endpoint (streamable-http) — https://api.seiche.info/palimpsest/mcp

Related, by what their authors tagged them

• cn.housingsentinel/housing-sentinel — last commit 2026-07-16, shares china
  中国12城官方房产成交数据与进攻/防守买卖信号 MCP。新用户免费试用3天（深圳）。Housing data & signals for 12 Chinese cities.
• io.github.cicicalex/engine — last commit 2026-08-02, shares ai-evaluation
  AIN bias & stability engine: finance, gaming, AI, crypto. 68 tools across 11 categories.
• Nahuali — last commit 2026-07-30, shares tamper-evident
  Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
• io.github.chernistry/bernstein — last commit 2026-08-06, shares tamper-evident
  Declarative agent orchestration for engineering teams
• io.github.cyanheads/internet-archive-mcp-server — last commit 2026-07-30, shares internet-archive
  Search the Wayback Machine and IA library (40M+ items), fetch snapshots, item metadata, and text.
• io.github.cyanheads/openlibrary-mcp-server — last commit 2026-07-30, shares internet-archive
  Search books and authors, fetch editions, browse subjects, and resolve cover images.
• dirtybeastafterthetoad-eu-ai-act-compliance-codebase-audit-skill-eu-ai-act-compl — last commit 2026-08-04, shares ai-safety, transparency
  Use this skill when answering questions about the European Union AI Act (Regulation (EU) 2024/1689) or conducting stati…
• life. scored. — last commit 2026-06-29, shares transparency
  Rebuilds the scores real systems run on you — credit, actuarial, lending — in the open, cited.
• AGTS MCP Server — last commit 2026-05-13, shares transparency
  Sovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.
• FYI MCP — last commit 2026-08-06, shares transparency
  FYI request management with tools for requests, authorities, correspondence, sync, and health.

These share tags the maintainers applied themselves, such as china, ai-evaluation, tamper-evident, internet-archive. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from beepboop2025

• data-breach-detector — last commit 2026-08-06
  Read-only breach intel, full history 2007-today: reports THAT an org was breached, never the data.
• io.github.beepboop2025/groundcheck — last commit 2026-08-06
  Verify claims, resolve FIGI identity, extract claims, and sign x402 delivery receipts over MCP.
• LiquiLens — the Failure Radar — repository gone
  Bank and lender failure early warning, with the validated record served beside every claim.
• io.github.beepboop2025/lucent — last commit 2026-07-19
  Pre-sign transaction-safety checks for signing agents (ERC-7730 descriptors).
• noisefloor — is this number real? — last commit 2026-08-02
  Is this number real, or is it noise? Peek-safe A/B tests, change detection, honest forecasts.
• io.github.beepboop2025/pdf-suite-mcp — last commit 2026-07-30
  37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
• io.github.beepboop2025/pdf-toolkit-mcp — last commit 2026-07-30
  37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
• Seiche — funding-stress terminal — last commit 2026-08-06
  Funding stress early warning for US money markets from free public data, with an honest backtest.
• io.github.beepboop2025/umbra-proof — last commit 2026-08-06
  Verify Umbra bridge accountability proofs (signed receipts, checkpoints, Merkle inclusion).
• Undertow — market liquidity map — last commit 2026-08-06
  Live exit costs by venue, depth concentration, and a sealed calls record that keeps its misses.

How the author describes it

Topics the maintainer set on GitHub: ai-censorship, ai-evaluation, ai-safety, censorship, censorship-monitoring, china, china-censorship, data-journalism, ddti, digital-rights, evals, great-firewall, internet-archive, internet-freedom, mcp-server, open-data, osint, tamper-evident, transparency, transparency-log.