Signetex
Server Details
Public AI claim register: E0-E4 evidence grades, forecast tracking, no verdicts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-03-26
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 9 tools
Most tools target clearly distinct resources or actions, such as get_entry, evidence_grades, latest_proof, register_stats, and track_record. The main overlap is between due_forecasts and list_due, which both surface forecasts by due date; descriptions distinguish relative-day lookup from an explicit date window, but an agent could still hesitate between them.
All names use snake_case, which is consistent, but the semantic pattern is mixed: some are action-first (compare_forecasts, get_entry, search_claims) while others are resource- or modifier-first (due_forecasts, evidence_grades, latest_proof, register_stats). The names remain readable, but they do not follow a predictable verb_noun convention throughout.
Nine tools is well-scoped for a read-only claims/forecast register, covering search, lookup, due forecasts, comparison, statistics, track record, evidence definitions, and proof status. Each tool appears to earn its place without excessive surface area.
The surface covers the core read-only workflows for this domain: search, entry lookup, due-forecast discovery, comparison, aggregate stats, track record, evidence definitions, and proof verification. A general browse/list-by-area or grade filter is not explicit, but search and stats provide reasonable workarounds.
Available Tools
9 toolscompare_forecastsBInspect
Show forecasts by different sources on one topic, drawn from public and MCP-only entries. Signetex grades evidence and issues no true/false verdicts.
Inputs: topic (required), area, limit.
due_forecastsBInspect
List register forecasts whose due date falls within the given number of days (including those already due and still open). Futures essays are not included. Signetex grades evidence and issues no true/false verdicts.
Inputs: within_days.
evidence_gradesAInspect
Return the published E0–E4 evidence-grade definitions from the Signetex method page, not a true/false scale.
Inputs: no named parameters.
get_entryAInspect
Get one register entry by its stable ID (for example SGX-AI-000031 or SGX-HU-000016), including sources, counter-evidence, grade rationale and history, with the canonical page URL. Signetex grades evidence and issues no true/false verdicts.
Inputs: id (required).
latest_proofAInspect
Return the latest published OpenTimestamps proof snapshot of the register (root hash, status, manifest URLs).
Inputs: no named parameters.
list_dueAInspect
List forecasts whose due date falls in the inclusive window from…to (YYYY-MM-DD). Returns public and MCP-only entries, including already closed ones in that window. Signetex grades evidence and issues no true/false verdicts.
Inputs: to (required), from (required).
register_statsBInspect
Headline counts for the published register: totals, areas, grades, forecast outcomes. A hit rate is only included once at least 30 forecasts have closed, as on the public site. Signetex grades evidence and issues no true/false verdicts.
Inputs: no named parameters.
search_claimsBInspect
Search the Signetex register of verified claims (public pages and MCP-only entries) across machine-intelligence, human-impact, politics-economy and corporate-promises. Internal or paywalled corporate entries are not included, nor are the speculative Futures essays. Returns matching entries with canonical URLs. Signetex grades evidence and issues no true/false verdicts.
Inputs: area, kind, grade, limit, +2 more.
track_recordAInspect
Return the closed-forecast record of a speaker or institution: counts of met, partial and not met, and a hit rate per register area. Uses public and MCP-only entries, never internal ones. Signetex grades evidence and issues no true/false verdicts.
Inputs: speaker, institution.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)
AI forecasting gym: markets, sports, policy and tech. Graded by reality, measured against markets.
Independent AI-agent reviews: trust checks, evidence scorecards, incident registry, recommendations.
Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian).
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceAuditable AGI-2027 evidence: eight graded Situational Awareness predictions with pre-registered flip conditions, a 0-100 Thesis Tracker with full score history, and a public market-call ledger where misses stay published. Free, no auth, CC BY 4.0.-
- AlicenseBqualityBmaintenanceForesea connects AI agents to prediction-market research: probability forecasts with cited evidence; Polymarket and Kalshi market scans, quotes, orderbooks and price history; weather and crypto analysis; and model-vs-market comparisons. Available through a hosted Streamable HTTP endpoint or a locally installed Python MCP server.28MIT
- AlicenseNot gradedqualityBmaintenanceTracks what an agent KNOWS vs INFERS vs ASSUMES with calibrated confidence. Provides tools to register, query, and analyze epistemic status of claims across domains.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables users to record probabilistic judgments in an immutable ledger, automatically score them against outcomes, and analyze systematic biases across six classification layers. It supports natural-language interaction for logging predictions, checking randomness, and auditing data integrity while avoiding advice or replacing user judgment.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.