qed.bot register
Server Details
Register of AI claims in mathematics, graded by the evidence behind each. Paid Lean proof checks.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
Search/get pairs map cleanly to distinct entities (statements, formalisations, targets), and check_proof/get_check form a clear submit-and-poll pair. The main overlap is between compare_registries and registry_positions, plus several analytical views over AI claims, though the descriptions differentiate them reasonably well.
All tool names use snake_case, and most follow a clear verb_noun pattern such as get_*, list_*, search_*, check_proof, and compare_registries. A few bare noun or noun-phrase names like benchmarks, disclosure, open_problems, and registry_positions are minor deviations but remain readable.
16 tools is slightly above the typical 3-15 range, but the domain spans statements, formalisations, targets, collections, evaluators, registries, and checks, so most tools earn their place. A few analytical views could potentially be consolidated, but the count is not excessive for the scope.
Core read coverage is strong: search and detail endpoints exist for statements, formalisations, and targets, with list endpoints for collections, evaluators, and systems, plus a check submit/poll lifecycle. However, list_evaluators references submit_construction, which is absent from this server, no get_collection or check-history listing exists, and there are no create/update operations for register entries, leaving notable dead ends.
Available Tools
16 toolsbenchmarksCRead-onlyInspect
Benchmarks as sets of statements, with how many members already carry public AI work: a contamination figure rather than a study.
Inputs: include_members.
check_proofAIdempotentInspect
Have qed.bot rebuild a Lean file at its commit and read what every theorem in it depends on, under the admission rules every stranger's file is held to. Costs one credit, or two for a private check; buy credits and make an API key at https://qed.bot/check, and send it as Authorization: Bearer qed_.... Returns at once with the check queued; call get_check until it is done, which takes minutes. A file already checked in public is returned free, and a check that stops on qed.bot's side is refunded.
Inputs: url (required), private, theorem.
compare_registriesBRead-onlyInspect
Results recorded by more than one registry, and how the positions differ. A disagreement is a difference of judgement about who did the mathematics; a gap is one registry holding stronger evidence than another; a lead is a proof somebody else records that this register has not rebuilt.
Inputs: limit, finding, registry.
disclosureCRead-onlyInspect
Announcements of results, graded for how much of what they claim can be inspected: whether each result is named, written up, and published with a checkable artifact.
Inputs: org.
get_checkARead-onlyInspect
A paid check's status and verdict, by the id check_proof returned. Needs the same API key for a private check.
Inputs: id (required).
get_formalisationARead-onlyInspect
One declaration in full: its sources, related formalisations, main results, the results held here it joins and on what key, Palomar's registrations of it, and any contradiction between what it declares and what a rebuild found.
Inputs: id (required).
get_statementARead-onlyInspect
Everything the register holds about one statement: formalisations, cited proofs, recompilation results, graded claims, relations and aliases.
Inputs: id (required).
get_targetARead-onlyInspect
Everything the register holds about one target: the record history with who held each value and when, the graded claims, and any check run here.
Inputs: id (required).
list_collectionsBRead-onlyInspect
The collections held, with counts of statements, formalisations and AI activity.
Inputs: no named parameters.
list_evaluatorsARead-onlyInspect
The object checkers available, what each establishes, what an artifact must look like, and which targets have been checked with it. Read this before calling submit_construction, which only the local server offers.
Inputs: no named parameters.
list_systemsCRead-onlyInspect
Track record per AI system, computed from recorded claims. Not a benchmark: which statements attract attention has little to do with how hard they are.
Inputs: name, limit.
open_problemsBRead-onlyInspect
Statements not recorded as solved, most valuable prize first. Use formalised_only to restrict to those a prover could attempt directly.
Inputs: limit, min_prize, collection, formalised_only.
registry_positionsCRead-onlyInspect
Every registry's position on one result, this register included, with each one's own label preserved beside the bucket it was placed in.
Inputs: id (required).
search_formalisationsBRead-onlyInspect
Every formalization.yaml the register has read, with what each declares about its own axioms, unproved goals, assumed literature, automation and review, and who has checked it: this register, Palomar, or nobody independent of its authors.
Inputs: flag, limit, query, method, +3 more.
search_statementsBRead-onlyInspect
Search the register of mathematical statements. Returns summaries with formal status, prizes, and how much AI work is recorded against each.
Inputs: limit, query, has_prize, collection, +3 more.
search_targetsCRead-onlyInspect
Search the targets: quantities with a direction and a record history, where AI work moved a bound or produced a better object rather than settling a statement.
Inputs: limit, query, standing, collection, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Public AI claim register: E0-E4 evidence grades, forecast tracking, no verdicts.
Read-only registry of AI-assisted scientific claims and where their evaluation stands (fr/en)
Open evidence base built by AI agents: server-checked quotes, blind review, Erdős literature checks.
Proofs checked, arXiv papers explained, LaTeX typeset by AI citizens; pay by card or USDC.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables rigorous, auditable mathematical proving with machine-checked steps, honestly distinguishing proven, refuted, and inconclusive results while disclosing unverified gaps.1MIT
- AlicenseAqualityBmaintenanceAirtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.1252 PyPI14Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables rigorous, machine-checked mathematical proving and proof review through 23 local tools that formalize propositions, verify each inference step with SMT and symbolic solvers, search for counterexamples, and run exact number-theoretic and high-precision arithmetic. Verdicts are strictly separated into proven, refuted, inconclusive, verified, sound_with_gaps, and flawed, so unproven steps are disclosed rather than hidden.MIT
- FlicenseAqualityDmaintenanceA calibrated faithfulness screen for informal↔Lean 4 statement pairs, served over MCP. It provides deterministic checks and deep LLM-based analysis to help draft Lean statements.27-
Glama MCP Gateway
Add one secure layer between your agents and this server.