Palimpsest — censorship, China economy and model-eval observatory
Server Details
Rights-aware censorship, China-economic status, and tamper-evident AI evaluation tools.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- beepboop2025/palimpsest
- GitHub Stars
- 3
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Most tools have clearly distinct roles: signal discovery, signal reading, newsroom/reporting surfaces, aggregate censorship verdict, rights metadata, and dataset catalog. Some overlap exists between get_newsroom, get_signal, whats_happening, and gfw_reading because they offer different levels of aggregation over related evidence, but the descriptions generally clarify when to use each.
All names use snake_case, but the verb/noun convention is mixed: get_signal, list_signals, inspect_economic_publication_rights, research_catalog, whats_happening, and gfw_reading do not follow one predictable pattern. The names remain readable, but an agent cannot infer the action pattern uniformly.
Seven tools is well-scoped for a broad read-only observatory spanning censorship, China economy, and model evaluation. The design uses broad discovery/read/aggregate tools rather than proliferating many narrow endpoints.
The set covers discovery, named signal retrieval, newsroom views, aggregate verdicts, rights metadata, combined GFW reading, and dataset catalog browsing. Minor gaps remain around explicit dataset-detail retrieval or search, but core observatory workflows are covered.
Publisher details
- Operator
- beepboop2025 · Publisher source
- Operator website
- https://github.com/beepboop2025 · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://www.palimpsest.info/developers.html · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Rights-aware public evidence; integrity proof does not establish completed validation or independent replication. · Publisher source
Available Tools
7 toolsget_newsroomEvidence and reporting desksARead-onlyIdempotentInspect
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 currently restricted China economic pulse, 'machine-analysis' for the currently restricted AnalysisReports and AbstentionReports, 'investigations' for review-gated research leads, 'editorial-readiness' for publication gates, and 'interconnection' for named-key fat-object joins on China situation events (topic-surface-only, never wire corroboration). The economy, machine-analysis and interconnection views are metadata-only until a lineage-filtered rebuild removes denied derivatives. Availability never implies publication readiness: statuses, gates, counterevidence, limitations and right-to-reply state stay attached.
Inputs: view, limit, status, priority.
get_signalOne signal's full readingARead-onlyIdempotentInspect
Read one named signal. Permitted signals return their bounded latest payload; China-economic signals in the denied lineage closure return explicit restricted/unavailable rights metadata and no values. 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, 'gfi-transcripts' returns a bounded view of the complete GFI v2 response matrix, and 'refusal-drift' returns the current frontier-model refusal reading on the frozen benign probe set; read 'eval-assurance' before turning either into a validity claim, and 'eval-journal' for the evidence-bound explanation and source receipts, or 'eval-findings' for the current deterministic article edition. Distinct from gfw_reading, which merges the two Great Firewall layers into one combined view.
Inputs: name (required), max_rows.
gfw_readingGreat Firewall: both layersARead-onlyIdempotentInspect
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'.
Inputs: no named parameters.
inspect_economic_publication_rightsInspect China data publication rightsARead-onlyIdempotentInspect
Inspect publication-rights metadata for China economic evidence. Returns the policy digest, UTC evaluation clocks, per-source decisions and published-record status. Takes no arguments and never reads or returns observation rows, derived signals or replacement values. A denied publication decision remains a restriction, not a zero observation.
Inputs: no named parameters.
list_signalsList published signalsARead-onlyIdempotentInspect
List every published signal Palimpsest exposes across its three 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. China economics: explicit metadata-only rights status for affected observations, pulse, forecast and derivative surfaces; no denied values are returned. AI model evaluation: the tamper-evident, pre-registered eval registry (hash-chained and Merkle-rooted), its claim-by-claim assurance ceiling, evidence-bound Eval Journal, deterministic live findings, and frontier-model refusal drift, alongside the Generative Firewall Index over a named China-focused panel. Takes no arguments. Call this first to discover signal names, then get_signal for one full reading.
Inputs: no named parameters.
research_catalogComplete research catalog and Seiche connectionCRead-onlyIdempotentInspect
Discover every Palimpsest dataset, including the latest China economic histories, external trade, regional research, information controls and model evaluations. Paginated metadata retains source clocks, rights and access states. Includes the Seiche research_network handoff for funding, institution and market-liquidity context; values are not copied.
Inputs: limit, offset.
whats_happeningCross-signal board verdictARead-onlyIdempotentInspect
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', 'eval-assurance' or 'refusal-drift'.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Signed, Bitcoin-anchored observations of AI training-data disclosure; verifies silence proofs, seals
Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.
Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Deterministic AI-liability attribution: signed, Bitcoin-anchored vendor/deployer/user fault split.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceDeterministic AI liability attribution engine. Scores fault across AI supply-chain participants (deployer, developer, vendor) with tamper-evident certificates and weekly cryptographic anchoring.’40 npm3Apache 2.0
- AlicenseNot gradedqualityDmaintenanceTamper-proof audit trail for AI decisions. 6 tools to record, verify, and export cryptographic proof chains via MCP.1Apache 2.0
- AlicenseBqualityBmaintenanceEnables AI assistants to query internet-censorship rankings, incident evidence, shutdown-risk forecasts, and Sentinel calibration data, plus optionally use an agent relay for identity, messaging, tasks, and trust.89MIT
- AlicenseNot gradedqualityBmaintenanceRuntime constitutional verification for AI answers — claim extraction with reasoning chains, Epistemic Confidence Score (ECS), 7-angle Glassbox Court red team, constitution compilation, Trust Card assembly, and deterministic SHA-256 audit logs.10Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.