Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Palimpsest — censorship and model-eval observatory

REMOTE · API.SEICHE.INFO · SCANNED AUG 3

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

Available components

+6 this week 70 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score →

Endpoint Security66
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
  • DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
Schema Quality & AI Usability75
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1137 tokens (~284/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

remote · api.seiche.info

# add to Claude Code
claude mcp add --transport http beepboop2025-palimpsest https://api.seiche.info/palimpsest/mcp
# ~/.codex/config.toml
[mcp_servers.beepboop2025-palimpsest]
url = "https://api.seiche.info/palimpsest/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "beepboop2025-palimpsest": {
      "type": "remote",
      "url": "https://api.seiche.info/palimpsest/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add beepboop2025-palimpsest --url https://api.seiche.info/palimpsest/mcp --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  beepboop2025-palimpsest:
    url: "https://api.seiche.info/palimpsest/mcp"
// mcp.json
{
  "mcpServers": {
    "beepboop2025-palimpsest": {
      "type": "http",
      "url": "https://api.seiche.info/palimpsest/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +2
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: good → excellent functional
  • 2 Aug 26 0
    • Schema quality: 154 → 294 functional
    • Schema quality: good → unverified functional
    • First check of Schema quality: 100 functional
  • 1 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 31 Jul 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 29 Jul 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Jul 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Jul 26 63

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Probed https://api.seiche.info/palimpsest/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.seiche.info CN=YE1,O=Let's Encrypt,C=US 9 Jul 2026 7 Oct 2026 ECDSA 256 ECDSA-SHA384 5124ecbed078faee1a2903ca8d3b4470ad0
SANs: api.seiche.info
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd
DNSSEC secure

Validation of api.seiche.info. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
info. present 5104 8 Verified
seiche.info. present 2371 13 Verified
api.seiche.info. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains; preload
content-security-policy default-src 'none'; frame-ancestors 'none'; base-uri 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=()
Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.seiche.info/palimpsest/mcp Verified 200
http (plaintext) http://api.seiche.info/palimpsest/mcp HTTPS enforced 308 https://api.seiche.info/palimpsest/mcp
MCP tools — 4 exposed · ~585 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
get_signal ~227

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.

NameTypeReqDescription
max_rowsintegercap on long row arrays (dataset, ranked, samples). Default 25 keeps a call small enough not to stall a tool loop; the generative-firewall-index dataset is 132 rows. Any cap applied is reported in the…
namestringyessignal name from list_signals, e.g. 'ooni-gfw', 'eval-registry' or 'refusal-drift'

No output schema declared.

No examples provided.

gfw_reading ~96

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'.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_signals ~142

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

whats_happening ~120

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'.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.